Skip to content
Back to search

agentic-scan

Read-only review skills for AI coding agents: twelve scans (security, privacy, architecture, performance, data integrity, logic, bugs, tests, UX, prompts, infra, pruning) that map an app and deliver findings as a dashboard and report.

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

Its scripts were only partly scanned.

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/simota/agentic-scan 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/simota/agentic-scan'

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/simota--agentic-scan/badge.svg)](/listings/simota--agentic-scan)

HTML

<a href="/listings/simota--agentic-scan"><img src="/api/listings/simota--agentic-scan/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 · 99 lines
  1. # agentic-scan
  2. Twelve read-only review skills for agents, kept in one repository. Each skill
  3. maps one aspect of an application, checks it, and delivers the findings as a
  4. dashboard and a report. None of them edits the code under review.
  5. ## The skills
  6. | Skill | Looks at |
  7. |---|---|
  8. | [`architecture-scan`](architecture-scan/) | Modules, dependencies and data ownership; layering, coupling, failure handling, operability |
  9. | [`bug-scan`](bug-scan/) | How bugs entered, from git history; the same entry points still present in code; a defect register |
  10. | [`data-integrity-scan`](data-integrity-scan/) | Write paths, schema and migrations; missing constraints, transaction gaps, lost updates |
  11. | [`infra-security-scan`](infra-security-scan/) | Terraform/OpenTofu, CloudFormation and Kubernetes config; exposure, identity, attack paths |
  12. | [`logic-scan`](logic-scan/) | Business rules; wrong results on realistic input, each with a counterexample |
  13. | [`performance-scan`](performance-scan/) | Hot paths; N+1 and unbounded queries, indexes, blocking I/O, caching, bundles |
  14. | [`privacy-scan`](privacy-scan/) | Personal data and where it flows; minimisation, consent, retention, third-party sharing |
  15. | [`prompt-scan`](prompt-scan/) | LLM prompts, templates and agent definitions; broken variables, contradictions, injection boundaries |
  16. | [`prune-scan`](prune-scan/) | What does not earn its place: dead code, unused features, flags, dependencies, config |
  17. | [`security-scan`](security-scan/) | Application source; authn/authz, cross-tenant access, injection, secrets, dependencies |
  18. | [`test-gap-scan`](test-gap-scan/) | The test suite; where a defect would slip through, and what to assert |
  19. | [`ux-scan`](ux-scan/) | Screens and flows; layout, states, forms, accessibility, microcopy |
  20. Each skill's own README describes its workflow and outputs.
  21. ## Diff mode
  22. Every skill can review a change instead of the whole repository: a branch
  23. against its base, a pull request, a commit range, or uncommitted work. Ask for
  24. it in the request:
  25. ```text
  26. /security-scan review only this branch against main
  27. /logic-scan the diff of PR 123
  28. /test-gap-scan my uncommitted changes
  29. ```
  30. Each skill's `scripts/diffscope.py` takes the diff from the merge base, as a
  31. pull request shows it, and the review covers the changed files and the code
  32. they reach. A finding is kept only when the change causes, exposes or worsens
  33. it; defects that were already there are mentioned in the chat summary, not
  34. recorded. The report names the range and says it is not a full assessment, so
  35. do not compare it with a full run. The procedure is in each skill's
  36. `reference/diff-mode.md`.
  37. ## Language
  38. The documentation is in English. Reports follow the user's language, chosen
  39. in this order:
  40. 1. A language named when invoking the skill, as an argument or in the
  41. request: `lang=ja`, `lang=en`, "in English", "日本語で".
  42. 2. Otherwise, the language the user has set for the agent: a host setting
  43. such as Claude Code's `language`, or a standing instruction such as
  44. "always respond in Japanese".
  45. 3. Otherwise, the language of the request.
  46. ```text
  47. /security-scan lang=en # English report, whatever the agent's language
  48. /ux-scan lang=ja # Japanese report
  49. ```
  50. The dashboards and reports are rendered in Japanese (`ja`) or English (`en`).
  51. For any other language the report is rendered in English and the agent's
  52. summary in chat uses the user's language. Each renderer also takes the
  53. language directly: `scripts/render.py ... --lang ja|en`.
  54. ## Layout
  55. ```
  56. agentic-scan/
  57. ├── Makefile fans a target out to every skill
  58. └── <name>/
  59. ├── Makefile link, unlink, status, test, check, demo (+ skill-specific targets)
  60. ├── README.md
  61. ├── skills/<name>/ the installable skill: SKILL.md, reference/, scripts/
  62. ├── examples/ sample findings used by check and demo
  63. └── tests/ offline tests
  64. ```
  65. Each `<name>/` directory was imported from its former standalone repository
  66. (`simota/<name>`) with its full git history.
  67. ## Usage
  68. From the repository root:
  69. ```sh
  70. make link # symlink every skill into claude / codex / agy skills dirs
  71. make status # what is linked, per skill and host
  72. make check # tests + self-containment checks for every skill
  73. make test ONLY="bug-scan ux-scan"
  74. make link AGENT=claude # AGENT, SKILLS_DIR, PYTHON pass through to each skill
  75. ```
  76. A failing skill does not stop the others; the run exits non-zero at the end
  77. and names the skills that failed.
  78. To work on one skill, run its own Makefile: `make -C ux-scan demo`.

Ratings and comments

Sign in to rate this skill.

Sign in

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