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/explorenpx skills add TheWinci/mimirs --skill exploregit 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/explore)<a href="https://agentmods.dev/skills/thewinci/mimirs/explore"><img src="https://agentmods.dev/badge/skills/thewinci/mimirs/explore.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 | $0.00079 | $0.00394 |
| Opus 5 | $0.00039 | $0.00197 |
| Sonnet 5 | $0.00016 | $0.00079 |
| Haiku 4.5 | $0.00008 | $0.00039 |
Grade A, and why
explore 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 3d 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
Explore
Goal: understand the area from real source before touching it. Prefer the mimirs tools over grep + reading whole files.
- Where is it —
search "<topic>"for ranked files, thenread_relevant "<topic>"to pull the actual functions/sections with line ranges (not just paths). Two chunks from one file can both appear. - How it connects —
project_map(focus: <key file>)for its neighborhood;dependents <file>for who relies on it;depends_on <file>for what it pulls in. - Read the core —
read_relevant "<specific behavior>"on the key files; follow the helper calls a named file delegates to. - History & why —
git_contextfor what changed recently;file_history <file>for how a file evolved;search_commits "<topic>"for why past decisions were made. - Prior context —
search_conversation "<topic>"andsearch_checkpoints "<topic>"for earlier discussion and decisions, so you don't re-derive what's already known. - Caveats —
get_annotationson the key files for known bugs, fragile spots, or constraints before trusting the code.
Finish: summarize in plain language — entry points, key files, data flow, gotchas — each with a file:line citation. Flag anything still unclear instead of guessing.
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.
- 3d ago First seen · 18 lines · 79 tokens per session scan A 7e4b1b1f54ce
explore is a skill published in the GitHub repository TheWinci/mimirs (29 stars, last pushed 19d ago), licensed Apache-2.0. It adds 79 tokens to every session and 394 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
akeneo-webhooks
Receive and verify Akeneo PIM (Events API) webhooks. Use when setting up Akeneo webhook handlers, debugging x-akeneo-request-signature verification, or handling batched product and product-model events like product.created, product.updated, product.removed, productmodel.created, productmodel.updated, or…
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
openai-webhooks
Receive and verify OpenAI webhooks. Use when setting up OpenAI webhook handlers for fine-tuning jobs, batch completions, or async events like finetuning.job.completed, batch.completed, or realtime.call.incoming.
replicate-webhooks
Receive and verify Replicate webhooks. Use when setting up Replicate webhook handlers, debugging signature verification, or handling prediction events like start, output, logs, or completed.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.