Skip to content
Back to search

Cypress

CYPRESS (Contextual Yield Protocol for Routed Expert Seed Systems) — a project- and vendor-agnostic multi-agent seed for AI coding tools. Drop it into any repo to give agents a large number of per-role expert team, named protocols, a progressive-discovery knowledge graph, and spec- and test-driven discipline by default.

Safety scan

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

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/llopresto87/Cypress with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/llopresto87/Cypress'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/llopresto87--cypress/badge.svg)](/listings/llopresto87--cypress)

HTML

<a href="/listings/llopresto87--cypress"><img src="/api/listings/llopresto87--cypress/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

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.

README.md · README · 115 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # CYPRESS
  2. ## What CYPRESS is
  3. CYPRESS is an installer that gives the AI coding [tool](DOCUMENTATION.md#term-tool) you already use a written way of working on your repository. It copies three kinds of file into the repository: instruction files, the method itself in Markdown, and a few small Python scripts that need only the standard library of Python 3.14 or newer. It is not a library your code imports, not a service and not a model. Installing only places those files; the work starts when you paste one prompt into a session of your tool, and that session reads your repository and builds its [knowledge graph](DOCUMENTATION.md#term-knowledge-graph): short linked notes about your project that later sessions open a few at a time instead of rereading the code.
  4. From then on, the method in those files asks each session to size its process to the task's risk, to write a [specification](DOCUMENTATION.md#term-specification) before the code and a failing test wherever a test can catch something, and to hand steps that need a clean context to separate [agents](DOCUMENTATION.md#term-agent); the glossary's [skill](DOCUMENTATION.md#term-skill) entry says how an agent differs from a skill. Most of this is asked of the model, and only part of it is checked by a tool: [What it does not do](#what-it-does-not-do) says which part is which.
  5. ## Who it is for and not for
  6. It is for developers who work in a code repository through a coding [harness](DOCUMENTATION.md#term-harness) the installer supports: Claude Code, Prime Agent, opencode, Codex or GitHub Copilot. Support is not the same on each: Claude Code, opencode (OpenCode 2) and Prime Agent are first-class, and Codex and GitHub Copilot are deprecated, installed only when you name them and given no new features. The [host capability matrix's support table](documentation/host-capability-matrix.md#support-tiers-adr-0009) and the host support decision records ([tiers](docs/decisions/adr-0009-host-support-tiers.md), [opencode](docs/decisions/adr-0033-opencode-first-class-on-opencode-2.md)) say what each level means.
  7. The method assumes no language, framework or stack. The reference [corpora](DOCUMENTATION.md#term-corpus) that ship with it are narrower: the library notes lean toward .NET, Java and Node.js, and the legal citations cover one national jurisdiction. Both are placed in your project only when you ask: the library notes page by page, from a list the installer proposes, and the legal citations whole. The [corpora reference](documentation/corpora-and-integrations-reference.md) has the breakdown.
  8. It is not for someone who does not use an AI coding [tool](DOCUMENTATION.md#term-tool), because nothing in the install acts until a session in that tool reads it.
  9. ## What installing does to your repository
  10. An install for Claude Code writes the files below into your project. If one of them is already there and differs, your version is kept beside it as a timestamped copy before the new one replaces it, and nothing is merged.
  11. - the [kernel](DOCUMENTATION.md#term-kernel), a short instruction file the harness reads at the start of every session: `CLAUDE.md` at the project root, with `AGENTS.md` beside it as a symlink to it (a copy where symlinks are unavailable); on the other harnesses, or where your project already has a plain `AGENTS.md` and no `CLAUDE.md`, `AGENTS.md` holds the kernel and `CLAUDE.md` is the symlink; with `--kernel-mode compose`, a team's own `AGENTS.md` stays as it is and `CLAUDE.md` imports it ahead of the kernel ([install guide](INSTALL.md#an-instruction-hub-your-team-already-keeps));
  12. - the harness directory `.claude/`, holding the agent definitions, the [skills](DOCUMENTATION.md#term-skill), slash commands, hook scripts and settings;
  13. - `docs/graph/`, where the knowledge graph lives: the method's own notes, and a skeleton that the first session fills in from your code, including `docs/graph/models.md`, where you name the model each host runs for each kind of work;
  14. - the install stamp `.cypress/seed.json`, which records the version and options of the install and keeps any key the installer does not own, and beside it `.cypress/recreated-nodes.txt`, which lists the method's notes this install had to put back because they were missing;
  15. - `EXPERT_SEED_INSTALL_PROMPT.md`, a local copy of the entry prompt for later sessions;
  16. - the [source index](documentation/source-index.md) cache under `.cypress/source-index/`, which the install's last step builds from your code. Git ignores it through a `.gitignore` inside it. The install then prints a short report of what the index found and what you still need to set up, with the fix for each item.
  17. Other harnesses get their own directory in place of `.claude/`, such as `.opencode/` or `.prime/agent/`, and the [install guide](INSTALL.md) lists each one.
  18. A file that already matches is left alone. The install stamp `.cypress/seed.json` and the list beside it are replaced without a copy ([backup before replace](DOCUMENTATION.md#enf-backup-before-replace)). Files under `docs/graph/` that belong to your project, such as the graph's index, are only added where missing ([project files kept](DOCUMENTATION.md#enf-plant-files-kept)), with one exception: the installer rewrites the `plant:` entry of `docs/graph/index.md` in place, also without a copy. It adds the entry if it is absent and writes each value you pass on the command line into a line still left as a placeholder, keeping any value already declared.
  19. The install does not touch your application source, `.gitignore`, git history or CI.
  20. ## What it costs
  21. | Figure | What it covers, and how it was obtained |
  22. |---|---|
  23. | 67 065 bytes | per session on Claude Code: the kernel, the one-line description of every agent and skill, and the orchestrator's charter with its always-loaded nodes, computed from the [seed](DOCUMENTATION.md#term-seed)'s files by this repository's test run; a lower bound, not a live reading |
  24. | 11% more tokens | per task, against a session with no method: 131 583 tokens against 118 973. The same run took 20% more tool calls (72 against 60) and 20% more wall-clock time (12 min 40 s against 10 min 32 s), and the run without the method found a defect that the run with the method missed. Measured once, on one small, well-specified task ([evidence record](docs/plans/grill-7.29.0-front-door/method-overhead-evidence.md)) |
  25. The always-loaded figure leaves out the notes a session opens on demand, each worker it starts, the text the hooks add to each prompt, and the one-time pass that builds the graph. The [host capability matrix](documentation/host-capability-matrix.md) gives the figure for each other harness. No money figure exists.
  26. ## Try it
  27. ```sh
  28. git clone https://github.com/llopresto87/Cypress
  29. ./Cypress/install.sh claude-code --project-dir /path/to/your/project
  30. ```
  31. You need bash and Python 3.14 or newer; with no Python at that version on `PATH`, the installer stops before it writes anything. The clone takes whatever the default branch holds when you run it, not a tagged release. In the second command, put your repository's path in place of the placeholder. That command only places files; its last line says the files are placed and the project's graph is not built yet. Then open a session rooted at your project and paste [`INSTALL_PROMPT.md`](INSTALL_PROMPT.md) into it. That starts the one-time [growth](DOCUMENTATION.md#term-growth) pass, which reads your repository and builds its graph. None of these steps asks you to learn the project's vocabulary first.
  32. On a first install, a harness may need a fresh session before it can start the agents that were just placed; the [delegation notes](core/method/delegation-bounds.md) record when, under `delegation.harness-registration`.
  33. <!-- first-screen-end -->
  34. ## How it works
  35. CYPRESS is a written [workflow](DOCUMENTATION.md#term-workflow), not a program. The session reads which steps a task needs and in what order, carries them out itself, and hands the steps that need a clean context to subagents. A few hooks and linters check parts of the work; the rest is left to the model and to you.
  36. The steps are written down as [protocols](DOCUMENTATION.md#term-protocol), procedures a session follows in order, and the [protocols reference](documentation/protocols-reference.md) lists them. The method asks each task to be sorted into a risk [tier](DOCUMENTATION.md#term-tier) first, from a question (T0) to a change to architecture or contracts (T3), and the tier decides how much process the task gets. A T3 change gets a specification, a failing test before the code ([test-first development](DOCUMENTATION.md#term-test-first)), and review by separate workers.
  37. Those workers are [specialists](DOCUMENTATION.md#term-specialist): roles such as `architect`, `tester` and `reviewer`, each defined in one file that names its tools and its model class. The [agents reference](documentation/agents-reference.md) lists all of them.
  38. Before reading code, a session is asked to open the graph's [router](DOCUMENTATION.md#term-router), an index that points to the few [nodes](DOCUMENTATION.md#term-node) a task needs, and to load only those. This is [progressive disclosure](DOCUMENTATION.md#term-progressive-disclosure) applied to your own project. Each fact is meant to live in one node, with every other node linking to it ([one home per fact](DOCUMENTATION.md#term-one-home-per-fact)).
  39. Once grown, your repository is a [plant](DOCUMENTATION.md#term-plant) of the [seed](DOCUMENTATION.md#term-seed), which is this repository. Lessons can travel between them later: [harvest](DOCUMENTATION.md#term-harvest) proposes a plant's lessons back to the seed, and [graft](DOCUMENTATION.md#term-graft) carries an updated seed onto a plant grown earlier. Only the [steward](DOCUMENTATION.md#term-steward) starts either one; the method may propose it and then waits ([steward only](DOCUMENTATION.md#enf-steward-only)).
  40. ## Why it is built this way
  41. A coding session works inside a fixed context window, and a session that has read everything has no signal about what matters. The always-loaded part therefore stays small, and the rest is looked up when a task needs it. Process is sized to risk, which spares a typo fix a feature's coordination cost. Specifications and tests come first, so a reviewer can check the work against something written before it. Steps that need a clean context go to separate workers, and one step's reading then does not crowd out the next. What the graph states is meant to be settled, so a later session uses it instead of working it out again. Only facts about your code can go stale, and a session checks those once, at its start, against the branch, commit and uncommitted changes recorded at the last [canonize](DOCUMENTATION.md#term-canonize) close-out.
  42. Each of these choices has a decision record, and the [decision index](docs/decisions/index.md) lists them with their status.
  43. ## What it does not do
  44. The method is written for the model to follow, and most of it is a request. For each mechanism, the manual's table of [what each control holds and misses](DOCUMENTATION.md#enforcement) names its class and its gaps.
  45. ### Requested, not enforced
  46. - Choosing a task's tier is the model's own call, and no tool sees a tier chosen too low ([tier classification](DOCUMENTATION.md#enf-tier-classification)).
  47. - Writing a specification before the code is asked of the model. A linter checks a written specification's shape, not when it was written ([spec before code](DOCUMENTATION.md#enf-spec-before-code)).
  48. - Writing a failing test before the code is asked of the model, and no tool sees the order ([test before code](DOCUMENTATION.md#enf-test-before-code)). Whether a contract needs a test at all is the architect's call, open to the tester's challenge; a check script refuses a test that only reads back what its change added, and only where your project runs it ([contract kind](DOCUMENTATION.md#enf-contract-kind), [worth check](DOCUMENTATION.md#enf-worth-check)).
  49. - Routing each task before reading anything and working through a protocol are asked of the model. The [routing](DOCUMENTATION.md#term-routing) hook adds the route to each prompt and holds nothing ([protocol order](DOCUMENTATION.md#enf-protocol-order), [prompt pointer](DOCUMENTATION.md#enf-route-hook)).
  50. - The linters report a fault only when someone runs them, and the install adds no CI to your project ([graph lint](DOCUMENTATION.md#enf-graph-lint), [this repository's own checks](DOCUMENTATION.md#enf-seed-gate)).
  51. - The kernel's byte budget is checked only in this repository's own test run, and nothing re-measures the copy in your project ([kernel budget](DOCUMENTATION.md#enf-kernel-budget)).
  52. ### Not yet measured
  53. - The overhead on a large task, one with a specification, several files and a rollback path: not measured. The one overhead figure above was measured once, on a small task.
  54. - The tokens the one-time growth pass spends on a repository: not measured.
  55. - Whether the method improves the quality of the work: not measured.
  56. - Whether owing a test only where it can catch something changes the number of tests a project writes or the tokens it spends: not measured.
  57. - Whether a host keeps the kernel's text after it compacts a long session: not recorded.
  58. ## Where to go next
  59. - [The manual](DOCUMENTATION.md), the long-form guide
  60. - [The glossary](DOCUMENTATION.md#glossary), one entry per project word
  61. - [What each control holds and misses](DOCUMENTATION.md#enforcement)
  62. - [Agents reference](documentation/agents-reference.md)
  63. - [Protocols reference](documentation/protocols-reference.md)
  64. - [Skills and templates reference](documentation/skills-and-templates-reference.md)
  65. - [Host capability matrix](documentation/host-capability-matrix.md)
  66. - [What's new in 8.0, 8.1 and 8.2](documentation/whats-new-8.md), with guides to the [source index](documentation/source-index.md) and to [placing corpus pages](documentation/corpus-placement.md)
  67. - [Decision index](docs/decisions/index.md)
  68. - [Install guide](INSTALL.md), including upgrade and removal
  69. - Per-harness notes: [Claude Code](integrations/claude-code/README.md), [Prime Agent](integrations/prime-agent/README.md), [opencode](integrations/opencode/README.md), [Codex](integrations/codex/README.md), [GitHub Copilot](integrations/github-copilot/README.md)
  70. - To upgrade a plant grown earlier, the [graft prompt](GRAFT_PROMPT.md); to fold a plant's lessons back, the [harvest prompt](HARVEST_PROMPT.md)
  71. - What changed in each release: the [changelog](CHANGELOG.md)
  72. ## License
  73. CYPRESS is released under the MIT License. See [`LICENSE`](LICENSE).
  74. Copyright (c) 2026 Luigi Lopresto.

Ratings and comments

Sign in to rate this skill.

Sign in

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