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/plannpx skills add TheWinci/mimirs --skill plangit 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/plan)<a href="https://agentmods.dev/skills/thewinci/mimirs/plan"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/plan.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 | $0.00075 | $0.00516 |
| Opus 5 | $0.00037 | $0.00258 |
| Sonnet 5 | $0.00015 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
plan 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
Plan
Goal: a concrete, ordered plan grounded in real source — and the blast radius of each proposed change before writing it.
- Understand the area —
search "<feature/topic>"for the relevant files, thenread_relevant "<behavior>"to read the actual functions/sections with line ranges. Don't plan against guessed code. - Where it lands —
write_relevant "<what you're adding>"for the best insertion point (file + anchor) for new code;project_map(focus: <key file>)for how the target neighborhood connects. - Impact of the change — for each symbol you intend to modify:
impact <symbol>(transitive callers as a pruned tree + the tests to run) so the plan accounts for every caller it ripples to. Widen withusages <symbol>(call sites) anddependents <file>(file-level importers).trace from=<a> to=<b>to confirm two symbols actually connect before relying on the path. - Prior decisions & caveats —
search_checkpoints "<area>"andsearch_commits "<area>"so the plan doesn't undo a deliberate choice;get_annotationson the files you'll touch for known bugs, constraints, or "don't refactor until X". - Resolve open decisions — before drafting, surface the choices the source doesn't settle (approach, scope, naming, tradeoffs) and ask the user. Don't guess past a fork that changes the plan; one round of focused questions beats a plan built on a wrong assumption.
- Draft the plan — ordered steps, each naming the
file:lineto edit, what changes, the callers it impacts (from step 3), and the tests to run. Call out risks and remaining open questions instead of hiding them.
Finish: present the plan for review before implementing — steps in order, impact per step, tests to run, prior decisions respected, each with a file:line citation. Let the user review before acting.
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 · 18 lines · 75 tokens per session scan A 19f335d0aa26
plan is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 21d ago), licensed Apache-2.0. It adds 75 tokens to every session and 516 once invoked, about $0.0004 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-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
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…
fireflies-webhooks
Receive and verify Fireflies.ai webhooks. Use when setting up Fireflies webhook handlers, debugging X-Hub-Signature verification, or handling the meeting.transcribed, meeting.summarized, and meeting.botjoined events from Webhooks V2. Also covers the legacy V1 scheme.
adyen-webhooks
Receive and verify Adyen webhooks (standard notifications). Use when setting up Adyen webhook handlers, debugging HMAC signature verification, or handling payment events like AUTHORISATION, CAPTURE, REFUND, CANCELLATION, and CHARGEBACK.