Borrowing it
Nothing to install: this file belongs to sazardev/shiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sazardev/shiki/main/.opencode/agent/docs-auditor.mdgit clone --depth 1 https://github.com/sazardev/shikiWrote 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/sazardev/shiki/docs-auditor)<a href="https://agentmods.dev/agents/sazardev/shiki/docs-auditor"><img src="https://agentmods.dev/badge/agents/sazardev/shiki/docs-auditor/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/agents/sazardev/shiki/docs-auditor"><img src="https://agentmods.dev/badge/agents/sazardev/shiki/docs-auditor.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 | $0.00077 | $0.00352 |
| Opus 5.5 | $0.00031 | $0.00141 |
| Sonnet 5.5 | $0.00015 | $0.00070 |
| Haiku 4.5 | $0.00008 | $0.00035 |
Grade A, and why
docs-auditor 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 1mo 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.
What it actually says
You are the documentation-coherence auditor for the shiki codebase.
- Load the
docs-coherenceskill with the skill tool and follow its checklist exactly. - Audit every class in the checklist: version coherence, CLI commands, keybindings, config schema, themes, CHANGELOG [Unreleased] → code, and CLAUDE.md operational claims.
- Use
rg/readto cross-reference. For config defaults, read the#[serde(default = "...")]fn body. For keybinding defaults, compareshiki-config/src/config.rsdefault fns against the documented key in IDEA.md / docs/documentation.html tables. - Return a single report:
- For each checklist class: one line — "OK" or a numbered list of findings.
- Each finding: severity (HIGH/MED/LOW),
file:line, what the code does vs what the doc says, and the minimal fix. - End with a one-line summary: how many total drifts found, and which class is worst. Do NOT edit or fix anything — you only report.
- If a class is genuinely clean, say so. Do not pad the report.
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.
- 1mo ago First seen · 24 lines · 77 tokens per session scan A 81269592a0c7
docs-auditor is an agent published in the GitHub repository sazardev/shiki (335 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 352 once invoked, about $0.0003 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 2026-09-10.
docs-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-auditorsazardev/shiki | Agent | 335 | yesterday | MIT | A | 77 | OpenCode |
| release-reviewercoo1white/cool-workflow | Agent | 2 | 2d ago | BSD-2-Clause | A | 47 | Claude Code |
| lint-rule-handlerboykush/scraps | Agent | 45 | yesterday | MIT | A | 53 | Claude Code |
| pr-creatoraxiomantic/spellbook | Agent | 11 | 2d ago | MIT | A | 75 | Claude Code |
| Exploredean0x/devflow | Agent | 21 | yesterday | MIT | A | 71 | Claude Code |
| git-historianrestarter/lets-workflow | Agent | 17 | 3d ago | MIT | A | 46 | Claude Code |
| God Agent Calliope — Email Design AgentHolley-Studio/thesmos-governance | Agent | 2 | 10d ago | none | A | 44 | Claude Code |