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 skills add Goldziher/poly --skill poly-lint-and-formatgit 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/skills/goldziher/poly/poly-lint-and-format)<a href="https://agentmods.dev/skills/goldziher/poly/poly-lint-and-format"><img src="https://agentmods.dev/badge/skills/goldziher/poly/poly-lint-and-format.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01531 |
| Opus 5 | $0.00021 | $0.00766 |
| Sonnet 5 | $0.00008 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
poly-lint-and-format 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
poly Lint and Format
Commands
poly lint [PATHS]…— run the linters. poly applies no fixes without--fix;--fixapplies autofixes (and the whole-project fix phase).--no-workspacerestricts to the per-file tier — and is also what makes a run read-only: without it, plainpoly lintstill executes the configured whole-project tools 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. Naming paths that narrow the run skips that phase by default (poly lint .names the repo root, so it does not narrow and the phase still runs);--workspaceopts back in, and the tools then cover the whole repository regardless of the named paths and of[discovery] exclude.poly fmt [PATHS]…— dry run by default: reports what would change and writes nothing.--fixwrites changes;--checkis the explicit form of the default dry run and conflicts with--fix.poly fmtis a pure formatter — it never runs the whole-project lint phase.
Flags
--format pretty|json|toon—pretty(the default) is the colored, human-oriented output;jsonand the compacttoonvariant are machine-readable. Under--format json/toon,poly lint's whole-project section and every note (discovery, skips, errors) go to stderr so stdout stays a single valid document — a machine consumer must check the exit code, not just the payload.--exclude <glob>— skip paths on top of.gitignore(repeatable; merged with[discovery] exclude). Gitignore-style: a glob without a leading/matches a directory of that name at any depth (e2e/**also prunessrc/test/java/io/xberg/e2e/), while a leading/anchors it to the config directory (/e2e/**).poly doctorwarns when a rule matches at more than one depth.--include-excluded— check explicitly named files or directory roots even when they match the exclude set. Exclusions below an included directory stay active. Applying the exclude set to explicitly named paths is already the default, so--force-excludeis accepted only as a compatibility no-op — the flag is parsed and never read.--config <path>— point at a specificpoly.toml.--no-cache— bypass the blake3 content-hash result cache.-j <N>— parallelism;--no-color— plain output;--verbose— extra per-finding detail inprettyoutput;--debug— per-engine cache hit/miss and timing, plus debug-level logs on stderr.--fix-generated— let--fixrewrite files markedDO NOT EDIT/@generated, which it otherwise reports on but leaves alone.--deny-skips/--max-skips <N>— strict coverage. A skipped file is one nothing inspected: a path named on the command line that no engine covers (App.csproj), or a file every routed backend declined (Go-templated YAML, a hash-stamped generated file). A skip the caller instructed —--only/--skipnarrowing an engine out, orenabled = falsein config — is not charged against the budget, since it names itself in the report rather than losing coverage silently; only a poly limitation counts. Skips are always reported and named; these flags make a chargeable skip fail the run (exit2), naming every file it fired on.--verboselists every skip inprettyoutput;--format json/tooncarries the full set both as a top-levelskippedarray and as syntheticresultsentries —summary.skippedis the authoritative count, so read it first and use the set only to name the files.
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 · +6 lines 6aabba70745e
- 7d ago First seen · 94 lines · 42 tokens per session scan A 6757a7754a59
poly-lint-and-format is a skill published in the GitHub repository Goldziher/poly (16 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 1,531 once invoked, about $0.0002 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 skills, from other repositories
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
argot-check
Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…
argot-write-rule
Codify a repo convention argot's built-ins don't cover into a scripted custom rule — a .argot/rules/NAME/rule.toml manifest plus a sandboxed Rhai script that fires exactly like a built-in, gated on a green fixture suite before it ever sees a real diff. Use when the user asks to "write an argot rule for X", "codify…
argot-refresh
Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…
argot-review-pr
Review a specific pull request (or diff range) against this repo's learned patterns with argot, without checking it out — flag dependencies, APIs, and constructs foreign to how the repo is written, duplicated functions, misfiled code, layering breaks, and tests weakened, disabled, or deleted alongside a production…
argot-suggest-rules
Turn a convention argot has already discovered into a scripted custom rule. Runs argot conventions, surfaces the repo's mined placement conventions (where a kind of code lives — "validation in schema files", "DB access only in migrations", "business logic in the service layer, not views") and internal-API vocabulary…