Borrowing it
Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/lint/SKILL.mdgit clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wikiWrote 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/vlasenkoalexey/tpu_performance_autoresearch_wiki/lint)<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/lint"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/lint/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/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/lint"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 184 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 185 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.03322 |
| Opus 5 | $0.00000 | $0.01661 |
| Sonnet 5 | $0.00000 | $0.00664 |
| Haiku 4.5 | $0.00000 | $0.00332 |
Grade A, and why
lint 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 11d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lint — run the SCHEMA LINT operation
Wraps SCHEMA's LINT operation as a standalone callable skill. Mostly mechanical; surfaces judgment calls for human review. Should be invoked periodically — drift accumulates silently otherwise.
When to invoke
- Periodic hygiene — every few days during active iteration, or weekly during quieter periods.
- At session end —
/stop-experimentStep 5 already runs LINT (this skill is the canonical implementation it points at). - Post-substantial wiki change — after a rename, a bulk import, a SCHEMA update, or a topic-taxonomy revision. Things drift when shapes shift.
- Pre-merge / CI — could be wired into git pre-push or a CI workflow to catch issues before they land.
- NOT during the autoresearch loop's normal cadence — LINT is too noisy + expensive to run per-iteration.
Cardinal rules
- Auto-fix mechanical issues (broken markdown links to renamed files, stale
updated:dates inconsistent with last edit, etc.). Surface what was auto-fixed in the report. - Flag judgment calls — anything that requires a human decision (contradiction adjudication, unresolved
[!warning]blocks, semantic alignment between Current best and latest supported experiment) — surfaces these as a punch list with file:line references. - Don't auto-commit. User reviews the auto-fix diffs + decides what to commit.
- Don't fail on first issue. Run ALL checks; produce a comprehensive report. A single broken link shouldn't hide 10 other issues.
Step 1 — Run every check from SCHEMA's LINT section
Per SCHEMA.md's "Operations → LINT" section. The canonical list (extend if SCHEMA gains new checks):
Cross-cutting wiki invariants
- Unresolved
[!warning]contradictions — grepwiki/**.mdfor> [!warning]blocks; report each with file:line + the contradicting claim. - Orphan pages — pages with zero inbound markdown links. Special case:
_-prefixed dirs/files inwiki/are auto-generated; SKIP orphan check for them (see also: AST snapshots underwiki/codebases/<slug>/_ast/). - Broken markdown links — relative paths whose target
.mddoesn't exist. - Concept/entity names mentioned in prose but not linked — heuristic: substrings from known concept page titles that appear unlinked in prose. Surface as advisory; many false positives.
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.
- 11d ago First seen · 186 lines · 0 tokens per session scan A 630ecf8b8767
lint is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,322 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 skills, from other repositories
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-running-evaluations
Execute TruLens evaluations and view results.
bug-reproducer
Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix. Also turn bug reports, stack traces, screenshots, failing behavior, support tickets, and regressions into minimal reproducible cases with red-to-green evidence. Use when…
proof-verify
Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work). For multi-stage work, seal accepted inputs with commit/tree, contract, input/output digests, and a fresh verdict so downstream stages do not…
testing-strategy
Use when planning or reviewing tests for a code change, choosing between unit, focused regression, integration, contract, end-to-end, performance, security, property-based, or agent-evaluation checks; classify change risk first and select the smallest evidence set that proves the behavior. Do not use for a single…
harness-feedback
Use when an agent says a test, VM, proof, evaluator, or release gate is overloaded, too strict, blocking staging, or causing false positives; split checks by profile, measure the burden, preserve high-risk evidence, and verify the smallest corrected workflow. Do not use for ordinary test selection, a single test…