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.
git clone --depth 1 https://github.com/btspoony/mstar-harnessWrote 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/btspoony/mstar-harness/codebase-audit)<a href="https://agentmods.dev/commands/btspoony/mstar-harness/codebase-audit"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/codebase-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/btspoony/mstar-harness/codebase-audit"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/codebase-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.00906 |
| Opus 5.5 | $0.00019 | $0.00362 |
| Sonnet 5.5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
codebase-audit 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 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.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Codebase
Run a read-only codebase audit that discovers what is worth doing and writes one prioritized review report under {REVIEW_DIR}.
Read-only. No source edits, no state machine, no commits. Output: the review report README.md at {REVIEW_DIR}/<date>-codebase-<level>-<round>/.
Boot
mstar-harness-coremstar-audit→ SKILL.md（common core：hard rules、recon、vet、variant dispatch、review report 输出）+references/codebase-audit.md（full-audit 变体：Phase 2 类别 + effort、scope variants、Phase 4 变体细则、review report 模板）mstar-roles→references/code-reviewer.md（执行角色：audit 执行体）mstar-conventions(path symbols —{HARNESS_DIR},{REVIEW_DIR})mstar-host→ active host reference (invoke capability for parallel subagents)
Routing（谁执行 audit）
| Context | Who runs the audit |
|---|---|
| Small repo (single scan pass feasible) | PM dispatches @code-reviewer — single scan pass, then vet and write the review report |
| Large repo (parallel categories needed) | @code-reviewer fans out read-only scout / explore subagents per category via Assignment Delegation: allowed (scout/explore only, read-only), then vets and writes the review report |
| Specialist depth needed | PM orchestrates an @architect consult for architecture/tech-debt depth (separate dispatch, or folded into the audit delegation brief) |
dsh host only. On dsh the large-repo fan-out goes through the native workflow tool, not subagent: after the operator types /codebase-audit, take the script + meta (meta.name: mstar-audit-fanout) from skill mstar-host → references/dsh-workflow-scripts.md (§ mstar-audit-fanout) — N≥3 read-only category seats, each agent() prompt opening with the Assignment header (Execute as: / Delegation: forbidden), one conversation workflow-run node. Other hosts unchanged (they keep their own invoke tool: task / Task).
This command is the PM entry point; the audit execution body is code-reviewer（PM dispatch）.
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 Changed · -2 lines · +1 tokens per session a031af9591a4
- 1mo ago Changed · +2 lines 93883a59176e
- 1mo ago First seen · 41 lines · 47 tokens per session scan A 8e8a5c9735f1
codebase-audit is a command published in the GitHub repository btspoony/mstar-harness (65 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 906 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
audit
You are a Principal Engineer & Product Architect conducting a full adversarial audit of this codebase. Your job is not to be polite. Your job is to find every structural, architectural, and experiential problem — then produce an actionable plan to fix them.
check-file
Perform comprehensive analysis of $ARGUMENTS to identify code quality issues, security vulnerabilities, and optimization opportunities.
refactor-code
Command "refactor-code" from centminmod/my-claude-code-setup, covering refactoring analysis command, your task, refactoring analysis framework, core principles (for analysis) and multi-agent analysis workflow.
review-spec
A command that reviews a software specification for accuracy, internal quality, and readiness for implementation. A specification describes what a feature should do and provides the reference for building it.
harness-review
Review the current change set from an opposing harness-engineering perspective.
book-style
A command for analysing how a novel is written, including its descriptions, actions, character thoughts, and dialogue.