Borrowing it
Nothing to install: this file belongs to pranee54/AgentDoctor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pranee54/AgentDoctor/main/.cursor/skills/agentdoctor-release-freeze/SKILL.mdgit clone --depth 1 https://github.com/pranee54/AgentDoctorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pranee54/agentdoctor/agentdoctor-release-freeze)<a href="https://agentmods.dev/skills/pranee54/agentdoctor/agentdoctor-release-freeze"><img src="https://agentmods.dev/badge/skills/pranee54/agentdoctor/agentdoctor-release-freeze/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pranee54/agentdoctor/agentdoctor-release-freeze"><img src="https://agentmods.dev/badge/skills/pranee54/agentdoctor/agentdoctor-release-freeze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00487 |
| Opus 5.5 | $0.00021 | $0.00195 |
| Sonnet 5.5 | $0.00010 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
agentdoctor-release-freeze scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AgentDoctor release freeze
Purpose
Prove the current 3.0.0 tree is correct, secure, and honestly documented before leaving it untouched. Version is already released.
When to use
- Final freeze / integrity audits
- After security remediation on a dirty tree
- Before human commit of remediation (do not auto-commit)
Non-negotiable rules
- DO NOT bump version, publish, tag, push, or create GitHub releases
- DO NOT invent features or redesign architecture
- DO NOT weaken security or delete tests to go green
- PASS requires evidence; NOT_VERIFIED must not become PASS
- Ownership ≠ containment (
OWNERSHIP_BOUNDARY_VERSION)
Workflow
- Read
docs/internal/AGENTDOCTOR_3_0_CURRENT_TRUTH.md(authoritative pointer) - Inventory CLI / dashboard / MCP from source, not memory
- Re-run hostile suites under
tests/unit/project/+ MCP transport + provider E2E - Fix only proven defects; add regressions
npm run verifythennpm pack+ clean-install smoke- Update freeze audit docs; leave commit to human
Verification checklist
-
npm pkg get version= 3.0.0 andPACKAGE_VERSIONmatches - CLI
--version= 3.0.0; dashboard HTML /ops.version= 3.0.0 - OPEN_P0=0 OPEN_P1=0 for security/correctness
- RELEASE_ACTIONS_PERFORMED=NONE
- Dirty tree reported if remediation present
Failure conditions
- Any foreign/
.private/symlink path becomes VERIFIED project intelligence - Stale Brain/Twin/Graph treated as current truth
- Model/dashboard/MCP grant write without real approval
- Hang on
$HOME/ broad roots
What NOT to do
Roadmaps, provider additions, version bumps, silent doc rewrites that erase historical audits.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago First seen · 46 lines · 52 tokens per session scan A ff722b1a755a
agentdoctor-release-freeze is a skill published in the GitHub repository pranee54/AgentDoctor (10 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 487 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other skills, from other repositories
stm
Screenshot every page of the running localhost dev server and report which pages changed since the last snapshot. Use after editing anything users can see (pages, components, CSS/Tailwind, layouts, templates) to visually verify before saying you're done, and when the user says "check the UI", "does it look right"…
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
harness-config-testing
Use when working in the harness-config repository on test strategy, regression coverage, fixtures, docs/TESTING.md, CLI end-to-end checks, projection edge cases, profile and ignore scenarios, or focused quality commands.
frontend-ui
Check layout states, responsive behavior, accessibility, and browser-visible regressions before claiming the UI works.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…