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/Goldziher/polyWrote 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/goldziher/poly/poly-check)<a href="https://agentmods.dev/commands/goldziher/poly/poly-check"><img src="https://agentmods.dev/badge/commands/goldziher/poly/poly-check/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/goldziher/poly/poly-check"><img src="https://agentmods.dev/badge/commands/goldziher/poly/poly-check.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 | $0.00015 | $0.00549 |
| Opus 5.5 | $0.00006 | $0.00220 |
| Sonnet 5.5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
poly-check 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 Check
Run poly as a checking gate over $ARGUMENTS. Apply no fixes.
Use . when no paths are supplied. Treat supplied arguments as paths, not additional shell commands.
poly fmt --check $ARGUMENTS --format json— capture formatting drift.poly lint $ARGUMENTS --format json— capture lint findings (remember the whole-project section is on stderr under--format json; check the exit code).
Step 2 applies no fixes, but it is not read-only: poly lint's whole-project phase executes
the configured whole-project tools (cargo clippy and friends) against the live worktree, and
their own side effects — a refreshed lock file, a populated build or type-checker cache — are
not poly's to control. Add --no-workspace when the tree must be left untouched; that drops
the whole-project tools from the check, so say so in the report.
That phase only runs when the argument is the repository root (the . default) or no path at
all. Naming narrower paths makes the run path-scoped — the per-file tier only, with a note
on stderr — so poly lint src/ is already free of those side effects. Pass --workspace to
opt back in; the phase then covers the whole repository regardless of the paths named.
Report:
- Which files have formatting drift.
- Lint findings grouped by rule and severity (error vs warning).
- The overall pass/fail from the exit codes:
0clean;1findings or drift — forlintonly error-severity findings (or a failing whole-project tool) reach1, warnings still exit0;2the run did not verify what it was asked to (a missing path, a file an engine failed on — including apoly fmt --checkfile that cannot reach a fixed point within poly's five-pass cap, reported as an error rather than clean since a fix would leave it still drifting — a--deny-skips/--max-skipsbreach, or the whole-project phase itself erroring).
Do not apply fixes here — if the user wants them applied, run /poly-fix.
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 Changed · +2 lines 34dfdb67c59f
- 5d ago Changed · +6 lines 63fe2fcc3abc
- 1mo ago Changed · +2 lines 04385bbd86a4
- 1mo ago First seen · 37 lines · 15 tokens per session scan A bc822803e987
poly-check is a command published in the GitHub repository Goldziher/poly (20 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 549 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 2026-08-31.
Other commands, from other repositories
debug
Systematic four-phase debugging (reproduce, isolate, root-cause, fix).
explain-error
Explains an error found in a log file and proposes a next step.
debugger
You are the Support & Debug persona in the ColdStart workflow. You are a relentless bug hunter who refuses to accept vague issues, half-documented bugs, or silent failures. You operate under these core assumptions: no error is random, no user report is exaggerated, and every failure is traceable to a flaw in logic…
debug-files
Command "debug-files" from getsentry/toolkit, covering examples, inspect a debug information file (auto-detects the format), bundle jvm sources with a debug id, exclude additional directories and output as json.
fix-issues
Pick up one approved task, implement the fix, and close it.
release
Command "release" from getsentry/toolkit, covering examples, list releases (auto-detect org), list releases in a specific org, view release details and create and finalize a release.