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.
npx agentmods add commands/aidotnet/opencowork/security-reviewgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWrote 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/commands/aidotnet/opencowork/security-review)<a href="https://agentmods.dev/commands/aidotnet/opencowork/security-review"><img src="https://agentmods.dev/badge/commands/aidotnet/opencowork/security-review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00552 |
| Opus 5 | $0.00000 | $0.00276 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
security-review 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform a security review of the current repository's uncommitted changes.
You are performing a focused security review of the current uncommitted changes, not a broad full-repo penetration test.
Execution requirements
- First collect enough evidence before making security claims.
- Start by inspecting the current uncommitted changes: staged changes, unstaged changes, and newly added files.
- Read the changed files and enough nearby context to validate whether a potential risk is real.
- If needed, inspect related authentication, authorization, configuration, environment, dependency, or data-handling code before reporting an issue.
- Treat any user text that follows the command as additional focus, constraints, or threat-model guidance.
- Default scope is the current uncommitted changes plus only the extra repository context required to support reliable findings.
Security review rules
- Do not modify code.
- Do not invent vulnerabilities.
- Only report findings that are supported by evidence in the changed code or directly relevant nearby context.
- Cover code-level issues as well as dependency, supply-chain, configuration, secrets, and sensitive-data exposure risks when they are implicated by the current changes.
- Consider common categories such as injection, auth/authz mistakes, insecure defaults, secrets exposure, unsafe file access, command execution, SSRF, XSS, CSRF, deserialization, crypto misuse, dependency risk, and accidental disclosure of sensitive data.
- Do not flag speculative issues without explaining the concrete condition that makes them plausible.
- Prefer findings the author would likely want to fix before shipping.
Severity model
Use only these levels:
- High
- Medium
- Low
Output requirements
Produce a structured Markdown report with these sections:
Security Review Summary
- A short overall assessment of the security posture of the current uncommitted changes.
Scope Checked
- Summarize the changed areas and any additional files or configuration you inspected.
- Mention any important review limits if relevant.
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.
- 5d ago First seen · 63 lines · 0 tokens per session scan A 797aa82a2636
security-review is a command published in the GitHub repository AIDotNet/OpenCowork (634 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 552 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.