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/jared833/claude-code-hooks/validate-accuracynpx skills add jared833/claude-code-hooks --skill validate-accuracygit clone --depth 1 https://github.com/jared833/claude-code-hooksWhat 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 | $0.00077 | $0.01077 |
| Opus 5 | $0.00039 | $0.00539 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
validate-accuracy 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
validate-accuracy
Validate site/src/lib/calculators/<slug>.js against the NEC source it claims to
implement. This is the accuracy check: a tool that fails here does not merge.
Core principle: do not trust the test file. The same model that wrote the calculator wrote its tests, so a shared misunderstanding passes tests while being wrong. Derivations here must come from the NEC data and formula directly.
Procedure
1. Fresh derivation (before reading the test file)
Open docs/specs/<slug>-spec.md and every site/src/data/nec-tables/*.json the calculator
imports. Choose at least 3 scenarios, covering every code path/branch of the calculator
(each conditional rule, for example NEC 240.4(B) round-up versus 240.4(D) small-conductor
caps, gets at least one scenario). For each, re-derive the expected outputs by hand from
the table values and the formula, writing out the arithmetic. Do NOT read
<slug>.test.js expectations until your derivations are committed to the worksheet.
2. Compare against actual output
Run the real calculator on each scenario, with a scratch node invocation:
cd site && node -e "import('./src/lib/calculators/<slug>.js').then(m => console.log(JSON.stringify(m.calculate({...}))))"
Any mismatch between derived and actual = FAIL. (Rounding: match the precision the tool displays; a discrepancy beyond display precision is a mismatch.)
3. Source-data spot check
For each NEC data JSON the tool uses, verify at least 3 entries against the published NEC values cited in the file's header comment (edition, table number). This catches transcription errors, the most likely failure mode for table-driven tools. A file whose header lacks the edition + table citation also fails.
4. External cross-check
Cross-check at least 1 scenario against a named independent third-party calculator (WebFetch). Name the specific tool and paste its URL in the worksheet; if the first one is unreachable, use a different named tool rather than skipping the step.
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.
- yesterday First seen · 98 lines · 77 tokens per session scan A 4d3bc77532b2
validate-accuracy is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 13d ago), licensed MIT. It adds 77 tokens to every session and 1,077 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.