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 allemaar/open-skills --skill map-initgit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/map-init)<a href="https://agentmods.dev/skills/allemaar/open-skills/map-init"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/map-init.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.01276 |
| Opus 5 | $0.00048 | $0.00638 |
| Sonnet 5 | $0.00019 | $0.00255 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
map-init 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/map-init
The onboarding door for Map Your Knowledge (MYK). It does exactly one job: make MYK the default way of working for the user's agents — with their explicit consent, on every agent platform they use, with every outcome reported exactly.
kernel-version: MYK v2.3
f2f96f2de49b4863bca55ee8f6004d24e00574a7db5e7e5ef0e3cb28c42510cf
Why every platform matters (say this to the user)
A knowledge graph is maintained by every agent that touches the vault. If one agent carries the rules and another does not, the uninformed one can undo in a session what the others maintain carefully. MYK works as a modus operandi only when EVERY resident agent loads it — that is why this skill offers the installation for all detected platforms, not just the one running it.
Steps
- Detect platforms. Identify every agent platform configured on this machine by its directive surface — e.g. Claude (
~/.claude/CLAUDE.md, projectCLAUDE.md/.claude/), Codex (~/.codex/AGENTS.md, projectAGENTS.md), and any other agent instruction file the user names. Read-only detection; never guess at unfamiliar formats — ask. - Check idempotently. For each platform, check whether the FULL payload is already present — all three elements: the load-the-rules routing clause, the orient-from-the-root-map clause, AND the born-mapped clause (a mere
map-rulesname reference is NOT installed; partial presence = offer to complete the missing clauses, shown as a diff). If the full payload is present everywhere: report "Nothing to do — you already have Map Your Knowledge installed" per platform, and stop. - Offer, with the choice and the benefits. For each platform missing the rules, present: (a) the choice — global (all projects) or project-local (this project's directive file only); (b) the exact text to be added (small, shown in full — see the payload below); (c) the benefits in plain words: agents orient from the scope's map before acting, new data is born mapped, existing structures are respected via the elastic verdicts, and every agent behaves consistently. This is optional and the user decides — per platform.
- Apply exactly what was consented. Insert the payload into the consented file(s) only. Show the diff before writing. Pre-check every consented target is writable BEFORE the first write; each file write is atomic; if a later platform's write still fails, report precisely which platforms succeeded and which did not, and offer the paste-fallback for the failed ones — the user is never left uninformed about a mixed state.
- Fallback: instruct, never force. Where automation cannot edit a platform's directives (unknown format, no file access, a hosted agent like a web UI), print the exact snippet plus per-platform instructions: where the file lives, where to paste, and how to verify (ask the agent "what do you do before organizing vault markdown?" — the answer should name the map rules).
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.
- 8d ago First seen · 65 lines · 96 tokens per session scan A 499d9cb9cbf9
map-init is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 21d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,276 once invoked, about $0.0005 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
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.