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 laurigates/claude-plugins --skill code-hidden-failuresgit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/code-hidden-failures)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/code-hidden-failures"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/code-hidden-failures/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/laurigates/claude-plugins/code-hidden-failures"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/code-hidden-failures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 10 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00045 | $0.02662 |
| Opus 5.5 | $0.00018 | $0.01065 |
| Sonnet 5.5 | $0.00009 | $0.00532 |
| Haiku 4.5 | $0.00005 | $0.00266 |
Grade A, and why
code-hidden-failures 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 16d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hidden-Failure Scanner
Detect code that fails without saying so. Two tracks:
| Track | Failure shape | Example |
|---|---|---|
| errors | Syntactic — an error signal is discarded | catch (e) {}, || true, 2>/dev/null, floating promise, _ = err |
| degradation | Logical — an operation "succeeds" with empty/useless output because a precondition was silently unmet | success toast on count === 0, if (!apiKey) return [], a 1-of-3 detector run with no indication |
Why one skill covers both tracks: references/history.md.
When to Use This Skill
| Use this skill when... | Use another skill instead when... |
|---|---|
| Scripts/CI report success but real work failed | /code:antipatterns — broad multi-category scan |
|| true, 2>/dev/null, empty catch {}, except: pass suspected (errors track) |
/code:review — prose code review |
| A feature reports success but produces nothing (degradation track) | /code:lint — a linter already flags the issue |
| Scans return 0 results / success banners on empty outcomes | /code:dead-code — you suspect code never runs |
| You need severity classification + a surfacing recommendation | — |
Context
- Scan path:
$ARGUMENTS(defaults to current directory) - Language signals: !
find . -maxdepth 2 \( -name '*.sh' -o -name '*.bash' -o -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.jsx' -o -name '*.py' -o -name '*.go' -o -name '*.rs' \) -type f -not -path './node_modules/*' -not -path './.git/*' - App-type signals (frontend): !
find . -maxdepth 2 \( -name 'index.html' -o -name 'vite.config.*' -o -name 'next.config.*' \) -type f - App-type signals (CLI): !
find . -maxdepth 2 \( -name 'bin' -type d -o -name 'Makefile' -o -name 'justfile' \) - App-type signals (service): !
find . -maxdepth 2 \( -name 'Dockerfile' -o -name '*.service' -o -name 'pyproject.toml' \) -type f - Config signals: !
find . -maxdepth 2 \( -name '.env*' -o -name 'config.*' -o -name 'settings.*' \) -type f - Workflows: !
find . -path '*/.github/workflows/*' -maxdepth 3 -name '*.yml' -type f
What ships with it
35 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fixtures/sample.sh 1.1 KB runs code
- REFERENCE-degradation.md 6.5 KB
- REFERENCE-go.md 3.6 KB
- REFERENCE-js.md 4.8 KB
- REFERENCE-python.md 4.1 KB
- REFERENCE-rust.md 4.1 KB
- REFERENCE-shell.md 3.7 KB
- REFERENCE-surfacing.md 5.7 KB
- references/history.md 280 B
- references/invocations.md 484 B
- references/no-ast-grep-fallback.md 539 B
- references/related.md 809 B
- references/report-format.md 803 B
- rules/lib/go-defer-close-unchecked.yml 197 B
- rules/lib/go-ignore-underscore.yml 237 B
- rules/lib/js-empty-catch.yml 152 B
- rules/lib/js-promise-catch-empty.yml 242 B
- rules/lib/js-void-ignore.yml 184 B
- rules/lib/py-bare-except-pass.yml 259 B
- rules/lib/py-broad-except-pass.yml 282 B
- rules/lib/rs-let-underscore-result.yml 181 B
- rules/lib/rs-ok-discard.yml 153 B
- rules/sgconfig.yml 852 B
- rules/tests/go-defer-close-unchecked-test.yml 284 B
- rules/tests/go-ignore-underscore-test.yml 222 B
- rules/tests/js-empty-catch-test.yml 135 B
- rules/tests/js-promise-catch-empty-test.yml 232 B
- rules/tests/js-void-ignore-test.yml 74 B
- rules/tests/py-bare-except-pass-test.yml 173 B
- rules/tests/py-broad-except-pass-test.yml 215 B
- rules/tests/rs-let-underscore-result-test.yml 180 B
- rules/tests/rs-ok-discard-test.yml 206 B
- scripts/scan-shell.sh 5.8 KB runs code
- scripts/test-fixture.sh 1.9 KB runs code
- scripts/tests/test-rules-project.sh 4.1 KB runs code
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.
- 16d ago Changed c933d7937cd6
- 19d ago Changed · -26 lines b1c6ba533d4c
- 1mo ago First seen · 228 lines · 45 tokens per session scan A a4ef3d13b9f4
code-hidden-failures is a skill published in the GitHub repository laurigates/claude-plugins (59 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,662 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
verify-before-done
Before claiming work is fixed, done, passing or deployed.
audit-dead-code
Read-only hunt for dead and unused code across four labeled lanes (Knip for TS/JS, vulture for Python, gopls for Go, grep for shell and files no lane owns), each candidate adjudicated dead, uncertain or alive. Use when asked to 'find dead code', to find what is unused in a repository (exports, functions, orphaned…
godot
Godot 4 work in a project with project.godot, .gd or .tscn files. Use to verify a change in the running game, fix a headless GDScript test run that hangs or exits 0, hand-edit a .tscn, commit .uid files, or catch an invented API.
performance
Profiling-driven performance optimization: caching, query tuning, N+1 fixes, memory, and load testing. Use to diagnose a bottleneck or set performance budgets.
devils-advocate
Stress-test plans and proposals via systematic adversarial review. Assumption extraction, evidence check, failure scenarios, operational gotchas. Before implementation begins. Use when: asked to attack a plan or proposal ('devil's advocate', 'stress test', 'poke holes', 'what could go wrong'), or before implementation…
ci-log-interpretation
Use this skill when reading or analyzing CI logs from a Shopware GitHub Actions workflow to figure out why a build failed — phrases like "why did CI fail", "what broke the build", "check the pipeline", "interpret these logs", "debug this red build" — or whenever raw run logs, job logs, or check annotations from a…