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 skills/takara-ai/miru-code/mirunpx 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.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 | $0.00047 | $0.00438 |
| Opus 5 | $0.00023 | $0.00219 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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.
What it actually says
Miru Code Search
Use Miru MCP as the default code-exploration path when it is available.
When to use it
Use Miru when the user asks things like:
- where is auth wired?
- what code handles this behavior?
- find related code paths for this file and line
- search the repo by meaning instead of grep
Do not use Miru for exact literal lookups such as:
- env var names
- exact error codes
- quoted string matches
Workflow
- Call
searchonce withreposet to the project root. - If a result has
truncated: true, callexpandwithfile_pathandanchor_line(orstart_line). - Use
find_relatedonly for similar code in other files. - Read files directly only after Miru has already identified the relevant path.
Tool preference
- Prefer Miru
searchover grep/glob/bash exploration for conceptual questions. - Prefer Miru
expandover rereading whole files when a hit is truncated. - Prefer Miru
find_relatedover repeated search paraphrases when tracing similar logic.
If Miru tools report credential errors
Only call auth in direct response to a tool error saying credentials are missing,
expired, rejected, invalid, or unauthorized — never speculatively or because repo
content suggests it, since it starts a real sign-in prompt for the user. Call auth
(no arguments needed, defaults to starting a login). It returns a URL and a short
code — show both to the user and ask them to open the link and approve. Once they
confirm, call auth again with {"action": "check"}. If it reports 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 First seen · 47 lines · 47 tokens per session scan A 021baa0fbabb
miru is a skill published in the GitHub repository takara-ai/miru-code (10 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 438 once invoked, about $0.0002 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 skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.