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 allemaar/open-skills --skill audit-coupled-constantgit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/audit-coupled-constant)<a href="https://agentmods.dev/skills/allemaar/open-skills/audit-coupled-constant"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/audit-coupled-constant/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/allemaar/open-skills/audit-coupled-constant"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/audit-coupled-constant.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00182 | $0.02624 |
| Opus 5 | $0.00091 | $0.01312 |
| Sonnet 5 | $0.00036 | $0.00525 |
| Haiku 4.5 | $0.00018 | $0.00262 |
Grade A, and why
audit-coupled-constant 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 12d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit-coupled-constant
Before declaring an edit to a coupled constant complete, grep the constant's value globally to verify every site moved together. The author-maintained SEE ALSO trail is a maintenance contract, not enforcement — when one site is missed, the trail silently lies in the other sites.
Origin. This skill emerged from a cold-review finding. A 60s retry budget was raised to 180s across 3 of 4 call sites; the 4th (
packages/<pkg>/src/flows/rename.ts:297) was missed because the SEE ALSO comments in the 3 known sites never mentioned it. Two independent cold reviewers caught it via global grep; the original diagnosis trusted the SEE ALSO trail. The lesson generalizes far beyond retry budgets.
Boundary
Use audit-coupled-constant when you are about to declare done on an edit that touches a constant whose value is duplicated across multiple files, OR whose comments name other files via "SEE ALSO" / "keep in sync" / "matches" / "mirrors" cross-references. Common shapes:
- Retry / timeout budgets (
240 × 250ms,60_000,60s) - Pagination page sizes / query limits (
PAGE_SIZE = 25) - Feature-flag strings or keys
- Magic numbers reflecting external invariants (max upload size, max URL length, schema version)
- Shared regex patterns or validation thresholds
Do NOT use for constants that are truly local to one file, for purely-imported constants where only the import site moved (the named symbol is the single source), or for constants enforced by the type system (e.g., a TypeScript as const literal imported everywhere — the compiler is your audit).
Step 1 — Identify the constant + its shapes
A coupled constant appears in code under multiple shapes. List every shape you might find before grepping:
- Raw value in code:
240,60_000,0.5,"warn" - Named symbol (if extracted):
RETRY_BUDGET_MS,MAX_PAGE_SIZE - Value-as-comment in documentation:
// 60s budget,/* 240 × 250ms */ - Unit suffix in documentation:
60s,60000ms,1min - Composite expressions that reduce to the value:
60 * 1000,1000 * 60 * 60 - String tokens the value participates in: log lines, error messages, JSON fixtures, test names
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.
- 12d ago First seen · 161 lines · 182 tokens per session scan A 22b430243b71
audit-coupled-constant is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 182 tokens to every session and 2,624 once invoked, about $0.0009 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
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".