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/goldziher/poly/poly-fixgit clone --depth 1 https://github.com/Goldziher/polyWhat 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 | $0.00020 | $0.00407 |
| Opus 5 | $0.00010 | $0.00204 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
poly-fix 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 2d 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
poly Fix
Apply poly's autofixes over ${1:-.}, then verify.
poly lint --fix ${1:-.}— apply lint autofixes, and run the whole-project phase in fix mode (cargo sortin place,cargo machete --fix,cargo clippy --fix --allow-dirty --allow-staged;cargo denyhas no autofix and stays check-only).poly fmt --fix ${1:-.}— format files in place.poly fmtis a pure formatter and never runs the whole-project phase, in either direction; only step 1 does.- Re-check:
poly fmt --check ${1:-.} --format jsonandpoly lint ${1:-.} --format json.
The whole-project phase in step 1 runs only because the argument is the repository root (the
. default). Narrower paths make the run path-scoped — per-file autofixes only — unless you
add --workspace; --no-workspace suppresses the phase outright.
Report:
- What changed — files reformatted and lint rules auto-fixed.
- What remains — findings that need a hand-fix (auto-fix couldn't resolve them), grouped by rule and severity.
- The final exit status of step 3 (aim for
0). Note that steps 1 and 2 legitimately exit1when they changed something; only2means the run failed to verify.
To apply no fixes, use /poly-check instead. (Even there poly's whole-project phase executes
cargo clippy and friends against the live worktree; add --no-workspace if the tree must be
left untouched.)
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.
- 2d ago First seen · 33 lines · 20 tokens per session scan A d251ad2267fd
poly-fix is a command published in the GitHub repository Goldziher/poly (10 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 407 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.