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/spec-validatenpx skills add capitalone/context-specs --skill spec-validategit clone --depth 1 https://github.com/capitalone/context-specsWhat 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 | $0.00064 | $0.02426 |
| Opus 5 | $0.00032 | $0.01213 |
| Sonnet 5 | $0.00013 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade B, and why
spec-validate scanned grade B with 1 finding 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 3d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
1. **Discover Available Experts** — Use `ls .claude/skills/ | grep expert` (do not use Glob, as it may not resolve symlinks). How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Validate
Validate a mainspec and its slices using parallel foreground subagents for high-confidence issue detection, then apply the impactful findings as fixes directly to the spec files. Agent-first: no human-in-the-loop. Invoked headless by the harness dispatcher, walks the consensus → classify → fix → sentinel protocol, and exits.
Invocation Contract
Invoked by the dispatcher as: claude -p "/spec-validate <feature>", run from inside the feature worktree (the dispatcher cds into it — there is no print-mode --cwd flag).
Single argument: <feature> — kebab-case feature slug.
Inputs read from disk (paths relative to cwd):
specs/<feature>/mainspec.mdspecs/<feature>/slices/*.md- The codebase (subagents ground findings in actual code).
Outputs to disk:
- Edits to
specs/<feature>/mainspec.mdand/orspecs/<feature>/slices/*.mdfor impactful findings. specs/<feature>/validation-log.md— audit trail: all consensus findings, classification (impactful vs. nitpick), and which fixes were applied. For observability; not load-bearing for the dispatcher.specs/<feature>/.validated(empty sentinel).
Completion protocol (in order):
- Run 3-subagent consensus + expert review (Phases 1–2 below).
- Classify each 3/3 and 2/3 finding as impactful or nitpick (Phase 3).
- For each impactful finding: edit the affected mainspec or slice file in place.
- Write
specs/<feature>/validation-log.mdcapturing every finding, classification, and what was changed. git addall changes (edited spec files + validation-log.md), commit, push.touch specs/<feature>/.validated.git addthe sentinel, commit, push.
The sentinel is the final commit-and-push action. The dispatcher uses only the sentinel to advance to implementation.
Idempotency:
- If
specs/<feature>/.validatedalready exists, exit immediately. - If
specs/<feature>/mainspec.mddoes not exist, exit silently — the dispatcher's state machine should not have fired this skill yet; planning has not completed. - If validation-log.md exists but the sentinel does not (crash mid-write), the dispatcher's worktree wipe will discard any uncommitted log changes, so we re-run validation from scratch. Acceptable cost.
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.
- 3d ago First seen · 252 lines · 64 tokens per session scan B efc8c261e7d8
spec-validate is a skill published in the GitHub repository capitalone/context-specs (41 stars, last pushed 8d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,426 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…