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/marihq/mari-cc/polishgit clone --depth 1 https://github.com/MariHQ/mari-ccWrote 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/marihq/mari-cc/polish)<a href="https://agentmods.dev/commands/marihq/mari-cc/polish"><img src="https://agentmods.dev/badge/commands/marihq/mari-cc/polish.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 5.1 | $0.00015 | $0.00178 |
| Opus 5 | $0.00008 | $0.00089 |
| Sonnet 5 | $0.00003 | $0.00036 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
polish 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 6d 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.
This is a copy
89% identical to clarify — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Run the polish editorial verb from the mari skill on $ARGUMENTS (a path, a natural-language reference like "the changelog", or — if omitted — the file(s) just edited this session; ask if none).
Setup first: load PRODUCT.md / STYLE.md / FACTS.md if present, read a representative file for voice, resolve the register, and run mari detect <target> for ground truth. Then apply the verb's reference flow: references/reference-polish.md in the mari skill. Preserve the author's meaning and voice — rewrite, not delete. Finish by re-running mari detect and fix any findings the edit introduced.
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.
- 6d ago First seen · 10 lines · 0 tokens per session scan A 49b358248ce0
polish is a command published in the GitHub repository MariHQ/mari-cc (32 stars, last pushed 26d ago), licensed MIT. It adds 15 tokens to every session and 178 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to clarify, differing in 6 lines, and is treated as a copy.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.