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 commands/mathiasbourgoin/roster/harness-validatorgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote 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/commands/mathiasbourgoin/roster/harness-validator)<a href="https://agentmods.dev/commands/mathiasbourgoin/roster/harness-validator"><img src="https://agentmods.dev/badge/commands/mathiasbourgoin/roster/harness-validator.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 | $0.00025 | $0.01092 |
| Opus 5 | $0.00013 | $0.00546 |
| Sonnet 5 | $0.00005 | $0.00218 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
harness-validator 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Validator
Verify the integrity of the knowledge base harness: KB structure, installed auditors, rule coherence, hook configuration, and feedback loop wiring.
Steps
1. Check: KB Exists and Has Valid Structure
- Verify
kb/index.mdexists and lists all KB files. - Verify core files exist:
spec.md,properties.md,glossary.md. - For each file in the index, confirm it actually exists on disk.
- Check each KB file has
last-updatedfrontmatter. - Flag missing core files as Critical. Flag missing indexed files as Warning.
2. Check: Auditor Skills Installed
- Verify each required auditor skill exists in
skills/kb/:ambiguity-auditor.md— always requiredcode-quality-auditor.md— always requiredharness-validator.md— always required (self-referential check)spec-compliance-auditor.md— required only ifspecs/directory exists in project root[ -d specs ] && echo "spec-compliance required" || echo "spec-compliance optional"
- Check each has valid frontmatter with
description. - Verify installed copies exist in
.harness/skills/and any Claude compatibility copies in.claude/commands/(if install has been run). - Flag missing auditors as Critical.
3. Check: Rules Coherence
- Read
.harness/rules/first, then.claude/rules/compatibility copies if present. - Read agent definitions (e.g.,
agents/directory orAGENTS.md). - Verify: rules reference KB files that exist, agent instructions don't contradict rules, no orphaned rules referencing deleted agents.
- Flag contradictions as Critical. Flag orphaned rules as Warning.
4. Check: Hook Configuration
- Read
.harness/hooks/and any runtime hook projection such as.claude/settings.json. - Verify hooks don't block tools that agents need (e.g., a pre-commit hook that blocks Bash would break all agents).
- Check that hook commands reference valid scripts/paths.
- Flag blocking hooks as Critical. Flag missing expected hooks as Info.
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 · 118 lines · 25 tokens per session scan A 07193a6a73d9
harness-validator is a command published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 1,092 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.