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/firatcand/forge/learnnpx skills add firatcand/forge --skill learngit clone --depth 1 https://github.com/firatcand/forgeWhat 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 | $0.00028 | $0.01046 |
| Opus 5 | $0.00014 | $0.00523 |
| Sonnet 5 | $0.00006 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00105 |
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn
Delegate to learning-curator.
Triggers (any one makes the task "notable")
- Investigation took > 30 min
-
2 fix attempts before success
- Surprised by behaviour
- Found a non-obvious gotcha
- Made a non-trivial trade-off
- Bootstrapped something new (test framework, CI, infrastructure)
Process
-
Read the last commit + PR description + investigation file (if exists).
-
Extract:
- What we expected
- What actually happened
- Why
- What we'd do differently
-
Tag with relevant types.
-
Resolve the canonical learnings path.
docs/learnings/is gitignored (forge-dogfood publish-hygiene rule), so its single source of truth is the main checkout'sdocs/learnings/tree — not the working directory./pickup-taskhydrates worktrees bycp -rfrom the main checkout (skills/pickup-task/SKILL.mdlines 47–53), and/learnmust mirror that contract on the write side. Seespec/SPEC.md §Learnings storefor the canonical-store rule and why.Resolve the main checkout's absolute path via
git rev-parse --git-common-dir(which always resolves to the main checkout's.gitfrom anywhere — main or worktree). Compare againstpwd -Pso symlinked paths (e.g. macOS/var↔/private/var) don't trigger a spurious double-write:GIT_COMMON_DIR="$(git rev-parse --git-common-dir)" MAIN_ROOT="$(cd "$(dirname "${GIT_COMMON_DIR}")" && pwd -P)" PWD_REAL="$(pwd -P)" QUARTER="2026-Q2" # or current quarter, e.g. "$(date -u +%Y)-Q$((($(date -u +%m)-1)/3+1))" SLUG="kebab-case-slug-from-title" mkdir -p "${MAIN_ROOT}/docs/learnings/${QUARTER}" -
Refuse on collision. If
${MAIN_ROOT}/docs/learnings/${QUARTER}/${SLUG}.mdalready exists, stop and surface the conflict — pick a different slug, orEditthe existing learning instead of writing a new one. Do not silently overwrite a prior learning. -
Write the canonical record first to the main checkout's absolute path using the
Writetool. This is the load-bearing write; do not skip it even on errors elsewhere:
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 · 112 lines · 28 tokens per session scan A d4c515bae789
learn is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,046 once invoked, about $0.0001 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
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-verify
Verify Implementation - Run 5+1 dimension audit (tasks, spec compliance, constitution, knowledge-implementation consistency, tests, design consistency) and assign quality grade (S/A/B/C/D). Triggers: verify, audit, quality check, 驗證, 稽核, 品質檢查, 評級.
prospec-archive
Archive Changes - Archive completed changes, generate summary, sync requirements to feature specs, and gate archiving on Knowledge sync. Triggers: archive, spec sync, finalize change, 封存, 歸檔, 收尾, 規格同步.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.