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/MilindGaharwar/fettleWrote 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/milindgaharwar/fettle/security-review)<a href="https://agentmods.dev/commands/milindgaharwar/fettle/security-review"><img src="https://agentmods.dev/badge/commands/milindgaharwar/fettle/security-review/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/commands/milindgaharwar/fettle/security-review"><img src="https://agentmods.dev/badge/commands/milindgaharwar/fettle/security-review.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 | $0.00019 | $0.00251 |
| Opus 5.5 | $0.00008 | $0.00100 |
| Sonnet 5.5 | $0.00004 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
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 1mo 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.
This is a copy
88% identical to fettle-security-review — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Run a security review on the target path.
Procedure
-
Determine target. Use
$ARGUMENTSif provided, otherwise the current working directory. -
Run the scanner:
python3 -m fettle.security_review --path TARGET -
Present findings grouped by severity (CRITICAL/HIGH first).
-
For each finding, explain:
- What the vulnerability is
- How it could be exploited
- The recommended fix
-
Offer to fix the highest-severity findings automatically.
Scope
- Python: ruff S-rules (full) + semgrep OWASP
- TypeScript/JavaScript/Go: semgrep OWASP only
- Other languages: limited to semgrep generic rules
This is NOT a comprehensive security audit. It runs available static analysis tools. For production security assessments, complement with manual review and dedicated SAST tools.
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.
- 1mo ago First seen · 38 lines · 19 tokens per session scan A ece074691280
security-review is a command published in the GitHub repository MilindGaharwar/fettle (4 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 251 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to fettle-security-review, differing in 9 lines, and is treated as a copy.
Other commands, from other repositories
aitask-pickrem
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
aitask-trail
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
aitask-wrap
Wrap uncommitted changes into an aitask with retroactive documentation and traceability.
aitask-run-gates
Run a task's declared gates — the conversational front of the headless gate orchestrator engine. Dispatches unlocked machine-gate verifiers within their retry budgets, observes human gates without self-signalling, and reports.
aitask-add-model
Register a known code-agent model in models .json, optionally promote it to default across config/seed/DEFAULTAGENTSTRING.
aitask-reviewguide-import
Import external content (file, URL, or repository directory) as a reviewguide with proper metadata.