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 commands/lookatitude/guild/learngit 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 | $0.00135 | $0.04063 |
| Opus 5 | $0.00068 | $0.02031 |
| Sonnet 5 | $0.00027 | $0.00813 |
| Haiku 4.5 | $0.00014 | $0.00406 |
Grade A, and why
learn 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guild:learn — understand-everything
The single entry-point for all codebase-understanding capabilities. A thin
dispatcher over the learn-* skill family (guild:learn-map, learn-graph,
learn-onboard, learn-diff, learn-explain) AND the smart full learn-all path.
One implementation, two triggers (D3): the pipeline this command runs is
byte-identical to what /guild:init --learn and defaults.auto_learn: true
invoke. There is no separate codebase-understanding engine.
Sub-verbs are positional ARGUMENTS (D3 — one implementation, two triggers). Full command reference: https://guildstack.dev/docs.
Usage
/guild:learn smart full learn-all (detect + confirm + pipeline)
/guild:learn map CodebaseMap + architecture overview only
/guild:learn graph Deep semantic KnowledgeGraph only
/guild:learn graph --rigor=deep Deep graph, highest fidelity
/guild:learn knowledge Deep multi-modal knowledge tier (topics + wiki/diagram index + cross-modal links)
/guild:learn onboard Guided architecture tour only
/guild:learn diff Change analysis vs HEAD only
/guild:learn diff src/auth/ Change analysis scoped to path
/guild:learn explain src/billing/invoice.ts
/guild:learn explain "how does the auth flow work"
All five global flags + --dry-run apply. --rigor=deep runs the highest-fidelity graph/analysis pass.
No-arg form — smart full learn-all
/guild:learn with no sub-verb triggers the smart full learn-all path.
This is the core correction from the brief (learn-knowledge-convergence §"Core
Correction"): absent arguments mean "learn this workspace or project completely,"
NOT "missing argument, print usage, stop."
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 · 298 lines · 135 tokens per session scan A 020bd834d9de
learn is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 135 tokens to every session and 4,063 once invoked, about $0.0007 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.