Skip to content
Back to search

aegis-dev

Development marketplace for Aegis method-pack skills library

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ganyuanran--aegis/badge.svg)](/listings/ganyuanran--aegis)

HTML

<a href="/listings/ganyuanran--aegis"><img src="/api/listings/ganyuanran--aegis/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

New here? The fastest start is one prompt to your agent — the full install-and-verify flow is below.

Give this prompt to your AI coding agent:

Read https://github.com/GanyuanRan/Aegis, identify my current AI coding host, and install Aegis globally using the correct host guide. If the host is the official DeepSeek Harness (`dsh`), treat global/minimal installation as native profile-plugin installation with `dsh plugin --profile <profile> add "git+https://github.com/GanyuanRan/Aegis.git"`; do not silently substitute the direct-child compatibility path unless the plugin manager is unavailable and I explicitly approve compatibility mode. Restart or reload the host if needed, then run complete-install verification from the installed Aegis method-pack root. Do not run the doctor command from the target project directory. First locate `<aegis-method-pack-root>`, then run `cd <aegis-method-pack-root> && python scripts/aegis-doctor.py --write-config --json`. Treat the install as complete only if the JSON includes `"ok": true`, `"workspaceSupport": "available"`, and `"configStatus": "configured"`; if the host uses a separate skill discovery directory, also verify it with `--discovery-root <path>`; if the host guide declares a skill directory name prefix, also pass `--discovery-name-prefix <prefix>`. Also complete the selected host guide's native activation and automatic-entry checks; file discovery or a generic doctor result alone is not sufficient when the host provides a plugin, hook, or session-start bootstrap contract.

DeepSeek Harness also supports the official npm package `@ganyuan_ran/aegis`. Choose one channel per profile; see the [DSH installation, update and migration guide](docs/README.deepseek-harness.md#updating). The prompt above selects Git; npm installations use the scoped package name.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines
  1. {
  2. "name": "aegis-dev",
  3. "description": "Development marketplace for Aegis method-pack skills library",
  4. "owner": {
  5. "name": "Aegis Maintainers"
  6. },
  7. "plugins": [
  8. {
  9. "name": "aegis",
  10. "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
  11. "version": "2.15.2",
  12. "source": "./",
  13. "author": {
  14. "name": "Aegis Maintainers"
  15. }
  16. }
  17. ]
  18. }
README.md · README · 305 lines
  1. <p align="center">
  2. <a href="https://linux.do/t/topic/2108966/20" alt="LINUX DO">
  3. <img
  4. src="https://img.shields.io/badge/LINUX-DO-FFB003.svg?logo=data:image/svg%2bxml;base64,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" /></a>
  5. <a href="https://dev.to/_879c5a0279451d52e43c3/aegis-a-method-pack-for-more-reliable-ai-coding-agents-1gfm" alt="DEV.to">
  6. <img src="https://img.shields.io/badge/DEV.to-Article-0A0A0A?logo=devdotto&logoColor=white" /></a>
  7. <a href="https://github.com/GanyuanRan/Aegis/actions/workflows/ci.yml" alt="CI">
  8. <img src="https://img.shields.io/github/actions/workflow/status/GanyuanRan/Aegis/ci.yml?branch=main&label=CI" /></a>
  9. <a href="https://github.com/GanyuanRan/Aegis/releases/latest" alt="Latest Release">
  10. <img src="https://badgen.net/github/release/GanyuanRan/Aegis?label=Latest%20Release" /></a>
  11. <a href="https://github.com/GanyuanRan/Aegis" alt="GitHub Stars">
  12. <img src="https://img.shields.io/github/stars/GanyuanRan/Aegis?style=flat&label=Stars" /></a>
  13. <a href="https://atomgit.com/GanyuanRan/Aegis" alt="AtomGit Stars">
  14. <img src="https://atomgit.com/GanyuanRan/Aegis/star/badge.svg" alt="AtomGit Stars" /></a>
  15. <a href="https://olud.ai/project/ganyuanran-aegis.html" alt="Aegis on olud.ai">
  16. <img src="https://olud.ai/badge.php?tool=ganyuanran-aegis" alt="Aegis on olud.ai" /></a>
  17. </p>
  18. <p align="center">
  19. <img src="assets/aegis-hero.png" alt="Aegis architecture-driven AI coding agent hero banner" />
  20. </p>
  21. # Aegis
  22. <p align="center">
  23. <strong>Aegis Method Pack</strong><br/>
  24. Make your AI coding agent trustworthy: fewer reworks, safer changes, proof before "done".
  25. </p>
  26. <p align="center">
  27. <a href="README.md"><strong>English</strong></a>
  28. ·
  29. <a href="README.zh-CN.md"><strong>中文</strong></a>
  30. ·
  31. <a href="docs/current/AEGIS_FAST_TRACK_PLAYBOOK.md">Fast-Track Playbook</a>
  32. ·
  33. <a href="docs/current/AEGIS_FAST_TRACK_PLAYBOOK_ZH.md">速通秘籍</a>
  34. </p>
  35. > **Stop babysitting your agent.** Aegis makes your agent plan against your real
  36. > baseline before it edits, prove completion with fresh evidence, and leave simple
  37. > tasks alone — you get **fewer reworks, safer changes, and less blind trust in "done"**.
  38. ## What You Get
  39. Aegis is a method pack that makes AI coding agents work like disciplined
  40. engineers — so you don't have to watch them.
  41. - **Fewer reworks.** Your agent aligns with your project's real baseline —
  42. owners, contracts, boundaries — before touching code. It stops guessing, and
  43. so do you.
  44. - **Safer changes.** Measured on a frozen held-out A/B benchmark: contract
  45. pass rate **61.67% → 93.33%**, unsafe outcomes **13.33% → 0%**.
  46. - **Proof before "done".** Completion claims ship with fresh verification
  47. evidence, covered scope, and residual risk. You read evidence, not vibes.
  48. - **No ghost code.** Retired fallbacks and old paths are tracked or removed
  49. with a retirement trigger — technical debt stops accumulating silently.
  50. - **Simple tasks stay simple.** Trivial requests stay on the fast path;
  51. ceremony only appears when the task genuinely needs it.
  52. - **UI/UX rules on demand.** [UI/UX governance](skills/ui-ux-governance/SKILL.md)
  53. carries project design rules, lower user effort, and scoped experience evidence
  54. through design, implementation, review, and verification.
  55. - **One method pack, every host.** The same discipline works across Codex,
  56. Claude Code, OpenCode, Kimi, and other skill-aware hosts.
  57. > These numbers are bounded advisory evidence from Aegis 2.7.6 (2026-08-11),
  58. > not a measurement of this release, a universal-quality claim, or completion authority.
  59. > See [the full benchmark and its limitations](#measured-agentic-benchmark).
  60. ## Quick Install
  61. New here? The fastest start is one prompt to your agent — the full
  62. install-and-verify flow is below.
  63. Give this prompt to your AI coding agent:
  64. ```text
  65. Read https://github.com/GanyuanRan/Aegis, identify my current AI coding host, and install Aegis globally using the correct host guide. If the host is the official DeepSeek Harness (`dsh`), treat global/minimal installation as native profile-plugin installation with `dsh plugin --profile <profile> add "git+https://github.com/GanyuanRan/Aegis.git"`; do not silently substitute the direct-child compatibility path unless the plugin manager is unavailable and I explicitly approve compatibility mode. Restart or reload the host if needed, then run complete-install verification from the installed Aegis method-pack root. Do not run the doctor command from the target project directory. First locate `<aegis-method-pack-root>`, then run `cd <aegis-method-pack-root> && python scripts/aegis-doctor.py --write-config --json`. Treat the install as complete only if the JSON includes `"ok": true`, `"workspaceSupport": "available"`, and `"configStatus": "configured"`; if the host uses a separate skill discovery directory, also verify it with `--discovery-root <path>`; if the host guide declares a skill directory name prefix, also pass `--discovery-name-prefix <prefix>`. Also complete the selected host guide's native activation and automatic-entry checks; file discovery or a generic doctor result alone is not sufficient when the host provides a plugin, hook, or session-start bootstrap contract.
  66. ```
  67. DeepSeek Harness also supports the official npm package `@ganyuan_ran/aegis`.
  68. Choose one channel per profile; see the [DSH installation, update and migration guide](docs/README.deepseek-harness.md#updating).
  69. The prompt above selects Git; npm installations use the scoped package name.
  70. ## Measured Agentic Benchmark
  71. A frozen held-out A/B benchmark for Aegis 2.7.6 (2026-08-11) kept the Codex client, prompts, projects, tool policy, and requested the same `gpt-5.6-sol` / `xhigh` setting in both arms; only the Aegis projection differed. Across 120 valid runs on 20 cases,
  72. contract pass rate was **61.67% → 93.33% (+31.67 pp)** and unsafe outcomes were **13.33% → 0%**. The 95% case-cluster interval was **+15.00 pp to +50.00 pp**. This is bounded advisory evidence; review was arm-hidden technical review, not independent human review, and host events did not return the observed model identity.
  73. ![Aegis agentic benchmark: with and without Aegis](benchmarks/results/gpt-5-6-sol-xhigh-extended-20260811-v2-7-6.svg)
  74. [Sanitized JSON](benchmarks/results/gpt-5-6-sol-xhigh-extended-20260811-v2-7-6.json) · [English table](benchmarks/results/gpt-5-6-sol-xhigh-extended-20260811-v2-7-6.en.md) · [中文表格](benchmarks/results/gpt-5-6-sol-xhigh-extended-20260811-v2-7-6.zh-CN.md) · [Methodology](docs/current/AEGIS_AGENTIC_BENCHMARK_BASELINE.md)
  75. A newer [matrix-v7 standard snapshot for Aegis 2.10.8](benchmarks/results/gpt-5-6-sol-xhigh-standard-20260925-v2-10-8.en.md)
  76. covers 22 cases with one observation per arm and case. It uses a different run
  77. profile from the extended snapshot above and does not measure the changes in
  78. this release.
  79. ## Try Aegis Methods in a Coding Runtime
  80. [Autoloom](https://github.com/GanyuanRan/Autoloom) is our AI coding desktop
  81. client. It brings Aegis's change necessity analysis, complexity governance, and
  82. delivery review into development execution, helping you spend less time
  83. repeating instructions and inspect the evidence behind delivered changes.
  84. Currently available as a **Windows x64 Alpha**. The client is free; choose your
  85. model provider, which bills model usage separately.
  86. **[Explore Autoloom](https://github.com/GanyuanRan/Autoloom) ·
  87. [Download Alpha](https://github.com/GanyuanRan/Autoloom/releases)**
  88. ## Updating Aegis
  89. After a complete install has registered the current host, later updates can use
  90. natural language such as `update Aegis` or the explicit skill request
  91. `aegis:update`. The agent can route either form through the local update path:
  92. locate the installed method-pack root, use the host-scoped registry, and call
  93. `scripts/aegis-update.py` for the current host by default. Updating every
  94. registered host requires an explicit `--all` request. Aegis does not run
  95. background automatic updates by default.
  96. For DSH profile-managed bundles, use the host plugin manager instead of
  97. `scripts/aegis-update.py`: Git uses `aegis`, npm uses `@ganyuan_ran/aegis`.
  98. Follow the [channel-specific update steps](docs/README.deepseek-harness.md#updating)
  99. and verify the installed version after restarting the intended profile.
  100. ## Before You Use It
  101. Aegis is currently:
  102. > `Aegis Method Pack (runtime-ready)`
  103. It is **not** the full Aegis Platform, a daemon, a background runner, a runtime
  104. core, an authoritative `GateDecision`, an authoritative `PolicySnapshot`, or
  105. final completion authority. User instructions and target-project rules outrank
  106. Aegis guidance.
  107. The [global routing prefix](GLOBAL_USER_RULES_TEMPLATE.md) is an optional,
  108. manually copied host/profile projection. It does not install Aegis or prove
  109. skill discovery. If the host already has reliable Aegis bootstrap and routing,
  110. no extra global rule is usually needed. Otherwise, add the prefix at the very
  111. beginning of the existing global user rules without changing unrelated
  112. content.
  113. This copied prefix is not managed by `aegis:update`. Users who previously
  114. copied the retired Lite / Advanced profiles should replace only those old
  115. Aegis blocks with the unified prefix. The prefix follows the host or session
  116. activation mode, defaults to `auto` when none is declared, and leaves detailed
  117. workflow governance to the loaded Aegis skills. Host-native skill matching may
  118. still remain host-controlled.
  119. Activation mode defaults to automatic. To switch to explicit mode, run this
  120. from the installed method-pack root:
  121. ```bash
  122. cd <aegis-method-pack-root>
  123. python scripts/aegis-doctor.py activation-mode explicit
  124. ```
  125. Restart the host after changing activation mode. Details and host caveats live
  126. in [docs/current/AEGIS_ACTIVATION_MODE.md](docs/current/AEGIS_ACTIVATION_MODE.md).
  127. TDD mode defaults to `off`: Aegis does not automatically require TDD, and
  128. completion verification still applies. To enable automatic TDD routing when you
  129. want Aegis to choose strict, light, or skipped by task risk:
  130. ```bash
  131. cd <aegis-method-pack-root>
  132. python scripts/aegis-doctor.py tdd-mode auto
  133. ```
  134. You can also request strict TDD directly in a query with explicit markers such
  135. as `TDD Route: strict`, `strict TDD`, `test-first`, or
  136. `RED / GREEN / REFACTOR`.
  137. Details live in [docs/current/AEGIS_TDD_MODE.md](docs/current/AEGIS_TDD_MODE.md).
  138. ## Supported Hosts
  139. Aegis keeps a multi-host, plugin-installable distribution goal.
  140. | Host group | Current status | Start here |
  141. | --- | --- | --- |
  142. | `Codex`, `OpenCode` | Fresh evidence exists for the current method-pack scope | [Codex](docs/README.codex.md), [OpenCode](docs/README.opencode.md) |
  143. | `Claude Code`, `CodeBuddy`, `DeepSeek-TUI`, `DeepSeek Harness`, `Trae`, `GitHub Copilot`, `Qoder`, `Kimi Code CLI`, `ZCode`, `Grok Build` | Install guides exist; release-level fresh host smoke is still pending | [Claude Code](docs/README.claude-code.md), [CodeBuddy](docs/README.codebuddy.md), [DeepSeek-TUI](docs/README.deepseek-tui.md), [DeepSeek Harness](docs/README.deepseek-harness.md), [Trae](docs/README.trae.md), [GitHub Copilot](docs/README.copilot.md), [Qoder](docs/README.qoder.md), [Kimi Code CLI](docs/README.kimi-code.md), [ZCode](docs/README.zcode.md), [Grok Build](docs/README.grok-build.md) |
  144. | `CC GUI (JetBrains IDEA)` | Structural IDE plugin layer support for Claude Code / OpenAI-GPT provider paths; release-level fresh host smoke is still pending | [CC GUI](docs/README.cc-gui.md) |
  145. | `Antigravity CLI`, `Antigravity IDE`, `Antigravity App` | `Antigravity CLI` has installation and structural discovery evidence; live Aegis skill loading, task routing, and session refresh remain pending verification; `IDE/App` remain structural targets | [Antigravity](docs/README.antigravity.md) |
  146. | `Pi CLI`, `OMP`, `OpenClaw`, `Hermes Agent` | Structural Agent Skills / `SKILL.md` skill-host adaptations; release-level fresh host smoke is still pending | [Pi CLI](docs/README.pi.md), [OMP](docs/README.omp.md), [OpenClaw](docs/README.openclaw.md), [Hermes Agent](docs/README.hermes-agent.md) |
  147. | `Gemini CLI` | Retired; Aegis no longer ships or verifies a Gemini CLI adapter | [Compatibility Matrix](docs/current/AEGIS_HOST_COMPATIBILITY_MATRIX_SNAPSHOT.md) |
  148. Read the current host verdict before making support claims:
  149. - [Host compatibility matrix](docs/current/AEGIS_HOST_COMPATIBILITY_MATRIX_SNAPSHOT.md)
  150. - [Known limitations](docs/current/AEGIS_KNOWN_LIMITATIONS.md)
  151. ## Start Fast With Aegis
  152. After installation and host restart, use normal language. Aegis matches the
  153. method to the work; name a mode directly when you want less ambiguity.
  154. ```text
  155. Why does this login failure happen? Diagnose it before changing code.
  156. Grill me on whether we should ship a hosted version first.
  157. Aegis goal: Fix the auth refresh bug without rewriting the auth system.
  158. Review this diff independently before I merge it.
  159. ```
  160. Read the [Fast-Track Playbook](docs/current/AEGIS_FAST_TRACK_PLAYBOOK.md) for
  161. Aegis's lightweight operating model, how it differs from standalone skill
  162. packs, its five engineering moats, project workspace lifecycle, natural trigger
  163. phrases, controls, and troubleshooting. The Chinese version is
  164. [Aegis 速通秘籍](docs/current/AEGIS_FAST_TRACK_PLAYBOOK_ZH.md).
  165. Use these explicit requests when you need tighter control:
  166. - `Aegis goal: ...` frames scope, success evidence, and boundaries.
  167. - `Grill me ...` or `审问我 ...` starts a decision interview; it asks one
  168. decision question at a time and does not plan or implement.
  169. - `TDD Route: strict`, `strict TDD`, or `test-first` explicitly requests
  170. strict test-first work. TDD is otherwise `off` by default.
  171. - `aegis:first-principles-review` or `review this from first principles`
  172. pressure-tests a complex direction before implementation.
  173. - `aegis:update` updates the installed method pack through its host-aware path.
  174. For non-trivial project work, Aegis can passively reuse relevant canonical
  175. language from `CONTEXT.md` or a bounded context selected by `CONTEXT-MAP.md`.
  176. It activates domain modeling only when a term is resolved, ambiguous, renamed,
  177. deprecated, or conflicting. High-confidence existing facts may synchronize
  178. directly; unresolved domain decisions remain user-owned. Files are created
  179. lazily on the first resolved term and remain glossary-only. Stable bytes can be
  180. cache-friendly, but Aegis does not guarantee provider cache hits or savings.
  181. Aegis preserves Workflow Quality by keeping simple work light and expanding
  182. only when risk warrants it. For deeper method detail, read the
  183. [Workflow Guide](docs/current/AEGIS_WORKFLOW_GUIDE.md),
  184. [Workflow Quality Baseline](docs/current/AEGIS_WORKFLOW_QUALITY_BASELINE.md),
  185. [Complexity Governance Baseline](docs/current/AEGIS_COMPLEXITY_GOVERNANCE_BASELINE.md),
  186. and [TDD mode](docs/current/AEGIS_TDD_MODE.md).
  187. If a capability does not trigger as expected, use trigger-chain diagnosis:
  188. install/version visibility, host skill discovery, activation mode,
  189. `using-aegis` routing, task-to-skill matching, and context pressure. Read the
  190. [Trigger Health Baseline](docs/current/AEGIS_TRIGGER_HEALTH_BASELINE.md).
  191. ## For Maintainers
  192. Primary verification entry:
  193. ```bash
  194. bash tests/e2e/run-all.sh --full --host-profile fast
  195. ```
  196. Focused docs / method-pack checks:
  197. ```bash
  198. bash tests/e2e/boundary-compliance-check.sh
  199. bash tests/e2e/workflow-quality-check.sh
  200. bash tests/e2e/install-verification-policy-check.sh
  201. bash tests/e2e/layer1-fast-check.sh --host-profile none
  202. ```
  203. Read:
  204. - [docs/testing.md](docs/testing.md)
  205. - [Release checklist](docs/current/AEGIS_METHOD_PACK_RELEASE_CHECKLIST.md)
  206. - [Current authority map](docs/current/README.md)
  207. - [Contributing](CONTRIBUTING.md)
  208. ## Community & Extending
  209. - Feedback and discussion: [GitHub Discussions](https://github.com/GanyuanRan/Aegis/discussions) · [Issues](https://github.com/GanyuanRan/Aegis/issues) · [LINUX DO](https://linux.do/t/topic/2108966/20) · [DEV.to](https://dev.to/_879c5a0279451d52e43c3/aegis-a-method-pack-for-more-reliable-ai-coding-agents-1gfm)
  210. - Extend Aegis: write your own skill with `aegis:writing-skills`; see the [Workflow Guide](docs/current/AEGIS_WORKFLOW_GUIDE.md).
  211. - Follow along: [RELEASE-NOTES.md](RELEASE-NOTES.md) · [Releases](https://github.com/GanyuanRan/Aegis/releases)
  212. ## Aegis and Autoloom
  213. - **Aegis** is our open-source method pack for bringing engineering discipline
  214. to your existing AI coding host. It remains independently usable with
  215. multi-host support; Autoloom is not required.
  216. - **[Autoloom](https://github.com/GanyuanRan/Autoloom)** is our independent
  217. desktop product for experiencing Aegis's core methods in the coding runtime.
  218. Its client source code is not currently public. Its repository maintains
  219. downloads, release scope, and feedback.
  220. Autoloom carries the runtime-core direction while Aegis retains its method-pack
  221. boundary. The benchmarks on this page measure Aegis, not Autoloom. See the
  222. [product relationship](docs/current/AEGIS_PRODUCT_BASELINE.md#current-product-relationship-autoloom)
  223. for the boundary, or bring a scoped task to Autoloom and
  224. [share your experience](https://github.com/GanyuanRan/Autoloom/issues).
  225. ## Relationship To Superpowers
  226. Aegis is derived from **[Superpowers](https://github.com/obra/superpowers)**,
  227. created by [Jesse Vincent](https://github.com/obra). Superpowers pioneered
  228. composable, multi-harness agent skills. Aegis keeps that foundation and adds an
  229. architecture- and evidence-focused method layer for real software projects.
  230. Additional inspiration comes from
  231. [mattpocock/skills](https://github.com/mattpocock/skills), especially concise
  232. communication, shared language, and disciplined debugging patterns. These ideas
  233. were re-implemented in Aegis format rather than copied verbatim.
  234. ## License
  235. MIT License. See [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.