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 TheWinci/mimirs --skill scoutgit clone --depth 1 https://github.com/TheWinci/mimirsWrote 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/thewinci/mimirs/scout)<a href="https://agentmods.dev/skills/thewinci/mimirs/scout"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/scout.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 | $0.00060 | $0.00526 |
| Opus 5 | $0.00030 | $0.00263 |
| Sonnet 5 | $0.00012 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
scout 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 7d 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
Scout
Goal: a sourced recommendation for a project decision — and it persists. Web research evaporates; the point of this skill is that the comparison and the why land in mimirs memory, so a later session recalls "we evaluated X vs Y and picked Y" instead of re-researching. Where research answers a question from the codebase and deep-research writes a generic report, scout weighs external options against this project and records the verdict.
- Frame the decision — name what's being chosen and the constraints. Ground it in the project:
search/read_relevantfor what we already use (stack, existing deps, conventions) so the recommendation actually fits. A fast option that doesn't match the stack is not a real option. - Search the web —
WebSearchfor solutions, competitors, alternatives, and prior art. Cast wide first, then narrow to the serious contenders. - Dig into contenders —
WebFetchthe primary sources (docs, repos, release notes) for the specifics that decide it: features, tradeoffs, maturity, license, last release / activity, and known issues. Prefer source over summaries. - Test fit — for each contender, check it against the project from step 1: does it match the stack, the constraints, the conventions?
read_relevantthe code it would touch. - Compare — a short table: option, key tradeoffs, maturity/license, fit for this project. Pick one, with the reason.
- Persist —
create_checkpoint(typedecision) with the comparison, the choice, and why — this is the durable record; stamp the date and the versions you checked, since web facts go stale.annotatea file only when a finding pins to specific code (a CVE on the import site, a deprecated API on the call site) — not for general option notes, which have no file to anchor to.
Finish: the recommendation with its tradeoffs and source links, and confirm it's saved as a checkpoint (with date + versions) so a future session can recall the decision. Flag findings likely to age out.
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.
- 7d ago First seen · 18 lines · 60 tokens per session scan A 90427a5faef5
scout is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 23d ago), licensed Apache-2.0. It adds 60 tokens to every session and 526 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.