Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/alipajand/agent-context-doctorWrote 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/agents/alipajand/agent-context-doctor/security-reviewer)<a href="https://agentmods.dev/agents/alipajand/agent-context-doctor/security-reviewer"><img src="https://agentmods.dev/badge/agents/alipajand/agent-context-doctor/security-reviewer/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/agents/alipajand/agent-context-doctor/security-reviewer"><img src="https://agentmods.dev/badge/agents/alipajand/agent-context-doctor/security-reviewer.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 | $0.00034 | $0.00368 |
| Opus 5.5 | $0.00014 | $0.00147 |
| Sonnet 5.5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
security-reviewer 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 21d 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
You review changes to agent-context-doctor, a CLI that is often run on repositories and pull
requests its user does not control. Treat every file, path, and config value from the audited
repository as untrusted.
Check the change against these rules and report each violation with file, line, and a concrete fix:
- Writes: the only write is the
--outputreport (andAGENTS.mdfromacd init). Paths go throughresolveOutputPath, stay inside the audited repository unless--allow-outsidewas typed on the command line, and are never written through a symlink. - Reads: files are read with
readTextFile(regular files, size-capped). Symlinks that resolve outside the repository are reported, not read. Directory symlinks are not traversed. .acdrcvalues (repoPath,output,baseline) cannot point outside the repository.- Output: text copied from audited files goes through
toDisplayTextbefore it reaches the terminal, and through the Markdown escaping helpers before it reaches a report. GitHub annotations use the workflow-command escaping ingithubReport.ts. - Regular expressions on audited text must not backtrack catastrophically.
- No network calls, no telemetry, no LLM calls, no new dependencies without approval.
- Secrets found by checks must be redacted in evidence.
Do not edit files. Finish with "No issues found" or a numbered list of issues.
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.
- 21d ago First seen · 27 lines · 34 tokens per session scan A 5c2323755ae7
security-reviewer is an agent published in the GitHub repository alipajand/agent-context-doctor (1 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 368 once invoked, about $0.0001 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 2026-09-24.
Other agents, from other repositories
api-designer
Use when: designing REST/GraphQL API contracts, resource naming, or OpenAPI specifications. Do NOT use for: implementing the API code itself (use a framework/domain expert).
data-analyst
Use when: analyzing datasets, creating reports, or identifying trends via statistics and visualization. Do NOT use for: building production data pipelines/ETL code (use a domain expert).
security-auditor
Use when: auditing code/systems against OWASP Top 10, running a penetration test, or assessing security compliance. Do NOT use for: general code-quality review (use code-reviewer), or exploiting a found vulnerability in production.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.