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/lookatitude/guild/learn-mapnpx skills add lookatitude/guild --skill learn-mapgit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00232 | $0.04533 |
| Opus 5 | $0.00116 | $0.02266 |
| Sonnet 5 | $0.00046 | $0.00907 |
| Haiku 4.5 | $0.00023 | $0.00453 |
Grade A, and why
guild-learn-map 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 2d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use it
Use to produce the cheap-scan tier of the brownfield derived indexes
(the authoritative 7-stage spec is implemented in scripts/learn/) and to
anchor the rest of the learn-* family.
This skill is invoked two ways, running the same implementation (D3):
/guild:init(default). Stage 1 only →CodebaseMap+ a confidence-taggedarchitecture-map.mdstub. This is Init-DONE. The deep tiers are NOT built here and are NOT required for Init to complete./guild:learn map, or/guild:init --learn/defaults.auto_learn: true. The cheap scan still runs here; the deep tiers (guild:learn-graph,learn-onboard,learn-diff,learn-explain) run as the same family, on demand or at bootstrap. There is no second codebase-understanding implementation —init --learnand/guild:learninvoke these same skills.
When not to use it
Not for greenfield (interview-first; the graph build is skippable there). Not
for the deep semantic graph or reverse-spec (guild:learn-graph), tour
narration (guild:learn-onboard), diff/blast-radius (guild:learn-diff), or
file/module explanation (guild:learn-explain). Not for ingesting a single
external source (guild:wiki-ingest) or querying an already-built graph/wiki —
that is the bounded kg-query retrieval path (wired into
guild:context-assemble) / guild:wiki-query. Not a competing memory: every
index is a derived projection over .guild/wiki/ (canonical) + the repo,
rebuildable and deletable with zero data loss.
/guild:learn map emits NO capability proposals. The
guild.project_capability_profile.v1 emission (D1) belongs to the FULL Learn
pipeline (guild:learn step 12b), not to the cheap-scan tier. The cheap scan has
not built the evidence a candidate must cite — proposing a role from a file
inventory alone is exactly the "invented professions" failure the sparse-project
guard (cap-loc-D04) exists to prevent. Map maps; it does not propose.
Required inputs
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 257 lines · 232 tokens per session scan A 9818bd209d68
guild-learn-map is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 232 tokens to every session and 4,533 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.