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 sentasity/cadence --skill c-find-bugsgit clone --depth 1 https://github.com/sentasity/cadenceWrote 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/sentasity/cadence/c-find-bugs)<a href="https://agentmods.dev/skills/sentasity/cadence/c-find-bugs"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-find-bugs/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/sentasity/cadence/c-find-bugs"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-find-bugs.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 | $0.00085 | $0.01847 |
| Opus 5 | $0.00043 | $0.00924 |
| Sonnet 5 | $0.00017 | $0.00369 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
c-find-bugs 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 8d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/c-find-bugs
You hunt concrete, fixable defects. Each defect comes with a citation, severity, and a direction for fixing — not a vague "this seems off."
Invocation forms
| Form | Target | Token cost |
|---|---|---|
/c-find-bugs <design-folder> |
Design — logical defects in proposed system | Medium |
/c-find-bugs <plan-folder> |
Plan — execution bugs (missing deps, type mismatches, impossible steps) | Medium |
/c-find-bugs <branch-name> |
Code changes on a branch vs. baseline | Medium |
/c-find-bugs <file-path> |
One file's source | Light |
/c-find-bugs --repo |
Whole repo | Heavy — confirms before starting |
Default scope when no target is given: current branch's diff against main (or config.find_bugs.default_baseline). If on main itself, ask for explicit target.
Token-cost warning: --repo prints estimated scope (file count, approximate token count) and waits for explicit user confirmation. Other scopes start without confirmation.
What it checks
On code targets (branch / file / repo):
| Category | Examples |
|---|---|
| Correctness | Off-by-one, null-deref, wrong comparison operator, swapped arguments. |
| Logic errors | Conditions that can never be true, dead code paths, infinite loops, missing return statements. |
| Resource handling | Leaked file handles, missing connection close, unclosed transactions. |
| Concurrency | Race conditions, missing locks, double-checked locking bugs. |
| Error handling | Swallowed exceptions, generic except catches, missing error propagation. |
| Security | SQL injection, command injection, hardcoded credentials, missing auth checks. |
| API misuse | Wrong library calls, deprecated APIs, missing required parameters. |
| Time / date | datetime.utcnow() (deprecated), naive datetime comparisons, timezone leaks. |
On doc targets (design / plan):
| Category | Examples |
|---|---|
| Logical bugs in proposed flow | Race conditions described in design, ordering violations, missing failure modes. |
| Plan execution bugs | Tasks referencing functions defined nowhere; tests that test the wrong thing; commits before tests pass. |
| Dependency errors | Task B uses Task A's Touches: files or symbols but lists no Depends: [A] edge (parallel-execution hazard); a Depends: cycle; a task Reads: a file no task Touches: or that doesn't exist. |
| Type / signature mismatches | Task 3 says clearLayers(), Task 7 says clearFullLayers() — same function, different name. |
| Impossible steps | "Run make foo" when no foo target in Makefile. |
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.
- 8d ago First seen · 143 lines · 0 tokens per session scan A f1d23d63897e
c-find-bugs is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 13d ago), licensed MIT. It adds 85 tokens to every session and 1,847 once invoked, about $0.0004 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
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
shipyard-debugging
Use when encountering any bug, test failure, unexpected behavior, or error message — before proposing any fixes. Also use when you see tracebacks, exceptions, "not working" complaints, build failures, performance problems, or integration issues. If you're tempted to "just try changing X and see if it works", this…
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.