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 skills add takara-ai/miru-code --skill mirugit clone --depth 1 https://github.com/takara-ai/miru-codeWrote 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/skills/takara-ai/miru-code/miru)<a href="https://agentmods.dev/skills/takara-ai/miru-code/miru"><img src="https://agentmods.dev/badge/skills/takara-ai/miru-code/miru/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/skills/takara-ai/miru-code/miru"><img src="https://agentmods.dev/badge/skills/takara-ai/miru-code/miru.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 | $0.00104 | $0.00686 |
| Opus 5.5 | $0.00042 | $0.00274 |
| Sonnet 5.5 | $0.00021 | $0.00137 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
miru 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Miru Code Search
Use Miru MCP as the default code-exploration path when it is available.
When to use it
Reach for Miru first, before opening files, whenever you don't already know the exact path:
- starting a task in code you haven't seen, to find the entry points
- finding where to make an edit ("where is auth wired?", "what handles this behavior?")
- answering how, where or why something works
- tracing related code ("find related code for this file/line")
- checking docs or config
Exact token (identifier, quoted string, env var, error code) → locate. Otherwise → search.
locate also takes a regex wrapped in slashes (locate(literal="/foo\w+Bar/"), /…/i to ignore case) and, with no literal, lists files by name: locate(include=["**/*.test.ts"]). Use mode="files" to get just the matching paths. Grep/Glob are only needed for files Miru does not index (lockfiles, binaries, generated or git-ignored files).
Workflow
- Literal in the request?
locate(literal="<token>")— prefermode="locations"/"count". - Otherwise
search(query="<question>")once. truncated: true? The header givespath:start-end Symbolandanchor_line: read exactly those lines (ranged read,offset/limit), not the whole file — only if the snippet doesn't already answer.expandis the fallback for neighbouring chunks.find_relatedfor similar code elsewhere, not more context in the same file.- Read files directly only after Miru has already located the path.
repo is optional, set it for another repo. Reuse it on follow-up calls.
If Miru tools report credential errors
Only start Takara device login with auth in direct response to a tool error saying credentials are missing, expired,
rejected, invalid, or unauthorized — never speculatively, since it starts a real sign-in prompt.
auth with no arguments starts a login and returns a URL and a short code — show both to the
user. Once they confirm, call auth again with {"action": "check"}. If still pending, wait
for the user to confirm again before re-checking — don't poll in a tight loop.
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 Changed · +4 lines 57882d8db031
- 10d ago Changed · +9 lines · +57 tokens per session 0da3ba05b34b
- 25d ago Changed · +2 lines c71c23ac5081
- 1mo ago Changed · -17 lines 794750b8ea24
- 1mo ago First seen · 47 lines · 47 tokens per session scan A 021baa0fbabb
miru is a skill published in the GitHub repository takara-ai/miru-code (12 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 686 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
coderabbit-review
Use when you need to evaluate CodeRabbit PR comments and fix or reply.
doc-gather
Use when you need to gather context for a Jira ticket or PR. Resolves ticket metadata, clones relevant repos, collects candidate files, runs filtering pipeline, and produces workspace/context-package.json.
doc-post
Use this skill to post validation and review findings as comments on a GitHub PR or GitLab MR. Reads workspace findings files and formats them as inline or summary comments.
doc-review
Use this skill to perform adversarial review of AsciiDoc documentation against context sources. Checks factual accuracy, completeness, consistency, and hallucination. Produces workspace/review-findings.json.