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 agents/jscraik/agent-skills/04-validationgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/agents/jscraik/agent-skills/04-validation)<a href="https://agentmods.dev/agents/jscraik/agent-skills/04-validation"><img src="https://agentmods.dev/badge/agents/jscraik/agent-skills/04-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 | $0.00000 | $0.02655 |
| Opus 5 | $0.00000 | $0.01327 |
| Sonnet 5 | $0.00000 | $0.00531 |
| Haiku 4.5 | $0.00000 | $0.00265 |
Grade A, and why
04-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 5d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation and Checks
Table of Contents
- Repository checks
- Config-sensitive checks
- AI workflow checks
- Skill quality ladder
- PR gate structure
- Authoring-family contract behavior
- Failure handling
Repository checks
- Fresh-checkout command reachability:
bash scripts/bootstrap-ask.sh --json, thenpython3 bin/ask repo status --json. - Git hook readiness:
bash scripts/install-prek-hooks.shinstallsprekhooks and patches the generated shims to use a writable temporaryPREK_HOMEoutside Git metadata. This avoids repeated Codex sandbox failures on~/.cache/prek/prek.logand prevents cache writes from being confused with linked-worktree metadata locks. Runpython3 Infrastructure/scripts/validation-and-linting/git_metadata_preflight.py --jsonfrom the repository root before expensive hook gates; it fails closed on a currentindex.lock, denied metadata writes, or a locked current worktree.bash scripts/check-environment.shfails if the adapter or hook wiring is missing. bash Infrastructure/scripts/validation-and-linting/verify-work.sh(project-local default scope)bash Infrastructure/scripts/validation-and-linting/verify-work.sh --workspace-governance(explicit workspace scope)bash Infrastructure/scripts/validation-and-linting/check_path_ownership_boundaries.sh(blocks direct edits to runtime/projection surfaces including.agents/skills/**,.agents/plugins-runtime/cache/**,Plugins/cache/**, andruntime/**)- projection-refresh exception only:
PATH_OWNERSHIP_ALLOW_CACHE_WRITES=1 bash Infrastructure/scripts/validation-and-linting/check_path_ownership_boundaries.sh - default scope is staged diff locally and base-ref diff in CI; override with
PATH_OWNERSHIP_GUARD_SCOPE.
- projection-refresh exception only:
bash Infrastructure/scripts/lifecycle-and-sync/sync_skills.shpython3 Infrastructure/scripts/validation-and-linting/docs_lint.py --mode warn --config Infrastructure/docs-policy.jsonpython3 Infrastructure/scripts/validation-and-linting/validate_steering_uptake.py --jsonvalidates the steering uptake ledger when agent operating rules, review feedback uptake, or high-signal steering surfaces change. It also rejects unknown failure-category and improvement-type labels so uptake records use the documented taxonomy instead of vague local phrasing.bash Infrastructure/scripts/run-infrastructure-python.sh -m pytest scripts/testing/test_validate_steering_uptake.py -qproves steering uptake cannot pass as ceremony by rejecting records that lack operating failure, blocker, mechanism, or proof fields.- Interface-design changes should have tests that read as policy checks for authority, ownership, invariants, and operation-context errors. See Misuse-Resistant Interface Design.
just validate(orbash Infrastructure/scripts/validate_all.sh)python3 Infrastructure/scripts/skill-graph/plan_graph_lint.py .agents/PLANS.md- Use the repo-local wrapper above instead of the global
~/.codexverify-workhelper for this repository. python3 Infrastructure/scripts/validation-and-linting/validate_steering_uptake.py --jsonwhen Jamie gives repeated or high-signal steering about agent behavior.python3 Infrastructure/scripts/validation-and-linting/validate_sdk_runtime_lane_contract.py --jsonvalidates the Skills SDK runtime lane contract. Use it when work touches or reports SDK mechanical validation,codex exec --profile oss-local,codex exec --profile oss-cloud, local Tessl staging, or--tessl-live-privateexternal Tessl proof.- Scope policy reference: hook-governance-scope-defaults.md.
- Path ownership policy: 14-path-ownership-boundaries.md.
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.
- 5d ago First seen · 194 lines · 0 tokens per session scan A c13e9cda02c3
04-validation is an agent published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,655 tokens. 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 agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.