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 skills/capitalone/context-specs/fix-local-checksnpx skills add capitalone/context-specs --skill fix-local-checksgit clone --depth 1 https://github.com/capitalone/context-specsWrote 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/capitalone/context-specs/fix-local-checks)<a href="https://agentmods.dev/skills/capitalone/context-specs/fix-local-checks"><img src="https://agentmods.dev/badge/skills/capitalone/context-specs/fix-local-checks.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.01546 |
| Opus 5 | $0.00057 | $0.00773 |
| Sonnet 5 | $0.00023 | $0.00309 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
fix-local-checks 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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix-local-checks
A narrow specialist, not a second /implement-mainspec. The feature already
works — ./prds/<f>/run-prd-test.sh exits 0 by the time you run. Your only job is
to make the project's deterministic gate, scripts/local-checks.sh, pass by
fixing the underlying cause the failing checks point at. One focused pass, then
commit and exit.
You run headless, invoked by the dispatcher as /fix-local-checks <feature>
inside the feature worktree, after a deterministic auto-fix pass (local-checks.sh fix) already ran and the gate is still red.
The one thing that matters: fix the cause, never silence the check
A check passing is a proxy for the code being right, not proof of it. You can almost always turn a red check green the cheap way — suppress it, weaken it, or delete what it was guarding. Every one of those is forbidden. Your fix is only real if the check passes because the underlying problem is gone.
This is the whole reason you exist as a separate, constrained skill: the failing lint's error message is a remediation prompt — it tells you not just what is wrong but how to fix it. Follow the fix it describes; don't make the matcher stop matching.
How to run this skill
1. Read the failures (single source of truth)
Run ./scripts/local-checks.sh yourself and read its full output. The messages
carry the remediation hints — that's your task list. Don't rely on anything passed
in; re-derive state from the script.
2. Triage each failure
- Clear-mechanical — the fix is unambiguous and the message says how (a missing type/property, an import, a formatting residue, an obvious lint fix). Make it.
- Needs-judgment — the honest fix would change behavior, or the failure reveals the plan or spec is wrong (e.g. a layer-direction lint firing because the design put code in the wrong place). Do the best honest fix you can. If you can't fix it without guessing or cheating, stop — see step 5.
3. Fix the cause
Edit the source so the real problem is gone. Scope yourself to exactly what the failing checks require — no refactors, no new features, no cleanup of unrelated code. This is polish, not implementation.
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.
- 6d ago First seen · 106 lines · 114 tokens per session scan A aaf9c88e5484
fix-local-checks is a skill published in the GitHub repository capitalone/context-specs (41 stars, last pushed 12d ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,546 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…