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/emasoft/claude-plugins-validation/cpv-fix-validationnpx skills add Emasoft/claude-plugins-validation --skill cpv-fix-validationgit clone --depth 1 https://github.com/Emasoft/claude-plugins-validationWrote 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/emasoft/claude-plugins-validation/cpv-fix-validation)<a href="https://agentmods.dev/skills/emasoft/claude-plugins-validation/cpv-fix-validation"><img src="https://agentmods.dev/badge/skills/emasoft/claude-plugins-validation/cpv-fix-validation.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01956 |
| Opus 5 | $0.00034 | $0.00978 |
| Sonnet 5 | $0.00014 | $0.00391 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade A, and why
cpv-fix-validation 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Validation — Error-to-Fix Index
Overview
Central error-to-fix lookup. Maps validation errors to fix guides in references/.
Formatter canon — lint only, NEVER format (user directive)
NEVER run a FORMATTER on any file: no ruff format, no prettier, no mdformat, no markdown formatter. Formatters reflow content and corrupt the structured Markdown that skills, agents, TRDDs, wikimem, obsidian notes, and YAML frontmatter depend on.
- Markdown / mdz / docs / TRDD / wikimem: lint-only. Run
markdownlintin REPORT mode, then fix each finding BY HAND with Edit. NEVERmarkdownlint --fix. - Python / JS/TS: the LINTER's autofix is allowed —
ruff check --fix,eslint --fix. NEVER the FORMATTER (ruff format/prettier). - JSON / YAML / config: lint/report only, fix by hand. No
prettier --write.
Why: a formatter (and markdown --fix) rewrites files opaquely and breaks the careful structure the author maintains. This is the same discipline as the fixer-agent scope guard ("never reformat a file you weren't sent to fix").
Prerequisites
- Report from
/cpv-validate-* - Access to
references/
Instructions
The token-economical fix flow (validate → ledger → MECH → INTEL read-once → delta → terminate):
- Validate → compact ledger, not the full report.
remote_validation.py <mode> <root> --strict --json > <findings.json>, thencpv_fix_ledger.py build --json <findings.json> --text <ledger.txt>; read<ledger.txt>(by-file, MECH/INTEL split, BLOCKING pre-tagged) — never ingest the full.mdreport each iteration (cost ≈ turns × per-turn-context). - MECH first (zero-LLM). Auto-apply the
mechbucket withcpv_codemod.py apply --json <findings.json> --applybefore spending any model tokens. - INTEL fix-as-you-go, read-once. Per
intelfile: read ONLY the finding line ranges (tldr slice/Readoffset+limit), apply ALL its fixes in the SAME turn, never re-read. The recipe is the ledger's inlinesuggestion; openplugin-error-index.md/marketplace-error-index.mdONCE per rule-TYPE (jump via TOC), not per finding. Forcategory: architecture, usecpv-migrate-marketplace-architecture. - Delta re-validate → terminate. Re-validate, rebuild the delta ledger, feed
cpv_fix_loop_state.py record(CONVERGED / CYCLE / STALLED). Full loop: iterative-fix-loop.
What ships with it
28 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.
- references/cache-fixes.md 12 KB
- references/code-quality-fixes.md 36 KB
- references/documentation-fixes.md 9.9 KB
- references/empirical-loading-bugs.md 9.4 KB
- references/encoding-fixes.md 12 KB
- references/enterprise-fixes.md 19 KB
- references/error-index.md 1.6 KB
- references/hook-fixes.md 82 KB
- references/iterative-fix-loop.md 23 KB
- references/lsp-fixes.md 25 KB
- references/marketplace-error-index.md 10 KB
- references/marketplace-fixes.md 73 KB
- references/marketplace-upstream-drift.md 15 KB
- references/mcp-fixes.md 36 KB
- references/pipeline-migration.md 31 KB
- references/plugin-error-index.md 33 KB
- references/plugin-structure-fixes.md 86 KB
- references/plugin-validator-detailed-procedures.md 11 KB
- references/rules-fixes.md 11 KB
- references/schema-parity-contract.md 4.3 KB
- references/scoring-fixes.md 12 KB
- references/security-fixes.md 23 KB
- references/settings-marketplace-fixes.md 14 KB
- references/ship-binary-only-fixes.md 8.4 KB
- references/skill-fixes.md 65 KB
- references/skill-semantic-validation.md 5.7 KB
- references/telemetry-hazard-fixes.md 6.9 KB
- references/xref-fixes.md 11 KB
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.
- 4d ago First seen · 81 lines · 69 tokens per session scan A 07f894c7642e
cpv-fix-validation is a skill published in the GitHub repository Emasoft/claude-plugins-validation (4 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,956 once invoked, about $0.0003 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.
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…