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/thewinci/mimirs/wikinpx skills add TheWinci/mimirs --skill wikigit 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/wiki)<a href="https://agentmods.dev/skills/thewinci/mimirs/wiki"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/wiki.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 | $0.00038 | $0.01569 |
| Opus 5 | $0.00019 | $0.00785 |
| Sonnet 5 | $0.00008 | $0.00314 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
wiki 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Rebuild
Use the wiki MCP tool as the source of truth. This skill is only a workflow
wrapper; do not invent a separate wiki structure.
The generation prose — discovery rules, the source-first writing contract, the
self-check, and the per-page prompts (flow, screen, overview, mechanism) — is served from
markdown, using packaged defaults unless a project overrides them. To customize
it for a project, run wiki(eject) once: it writes the defaults to
.mimirs/wiki/*.md for you to edit, and a file there overrides the packaged
default. Edit instructions in .mimirs/wiki/, never the generated wiki/ output.
Core Rule
The wiki is flow-first. Create one page for one concrete trigger:
- one HTTP method + route
- one message, event, queue topic, or consumer handler
- one CLI subcommand
- one MCP tool
- one worker, job, schedule, webhook, or server start
Do not bundle all API endpoints into one page. Do not bundle all messages into one page. Do not create broad architecture, module, entity, glossary, or generic data-flow pages unless the human explicitly asks for those.
The sanctioned exception for shared internals is a mechanism page
(kind: "mechanism", slug mechanisms/<name>): one page per internal subsystem
that three or more flows call but that is nobody's entry point — ranking,
caching, graph traversal, or similar. Flow pages link to it instead of each
re-explaining the same internals.
If many flows share files, keep separate pages and connect them with related flows.
Workflow
- Call
index_files()if the project index is empty or stale. - Call
wiki(shape). - Use the returned prompt and prefetch selectors to create
wiki/_discovery.json(flows first, then the overview second pass, then the mechanism third pass). - Validate with
wiki(validate-discovery). - If validation reports errors, fix
wiki/_discovery.jsonand validate again. - If validation passes, ask the human whether to continue.
- If the human says yes, call
wiki(write). - Read
wiki(discovery)and split the work by page slug. - For each slug, call
wiki(write:page:<slug>). - Write only the assigned page under
wiki/. - After all page writers finish, call
wiki(validate-pages)and fix any broken relative.mdlinks it reports. - Before committing the updated pages, call
wiki(changelog)and follow the returned prompt: it diffs the pendingwiki/changes and has you prepend one entry towiki/CHANGELOG.md— a curated summary of the behavior changes for an incremental update, or a single line for a full regeneration. Then commit the pages and the changelog together.
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 · 139 lines · 38 tokens per session scan A 206b1c766305
wiki is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 21d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,569 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 2026-08-30.
Other skills, from other repositories
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
azure-event-grid-webhooks
Receive and validate Azure Event Grid webhook deliveries. Use when setting up an Event Grid WebHook event handler, implementing the Microsoft.EventGrid.SubscriptionValidationEvent handshake (echo data.validationCode as validationResponse with HTTP 200), implementing the CloudEvents v1.0 HTTP OPTIONS abuse-protection…
baselinker-webhooks
Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature…
clio-webhooks
Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the X-Hook-Secret handshake, or handling legal practice events like matter.created, contact.updated, activity.created, or bill events.
favro-webhooks
Receive and verify Favro webhooks. Use when setting up Favro webhook handlers, debugging X-Favro-Webhook signature verification, accepting the setup ping, or handling card events (card.created, card.committed, card.moved, card.updated, card.deleted) and comment events (comment.created, comment.updated…