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/pickup-tasknpx skills add firatcand/forge --skill pickup-taskgit 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 | $0.00034 | $0.02084 |
| Opus 5 | $0.00017 | $0.01042 |
| Sonnet 5 | $0.00007 | $0.00417 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade C, and why
pickup-task scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
running `/wrap-up`. Handle both shapes: `[ -L node_modules ] && rm node_modules || rm -rf node_modules` (run INSIDE the worktree — never against the main checkout). How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pickup-task
Status queries always hit the tracker.
plans/phases.yamlis a stale cache. See your projectCLAUDE.md§Source of truth.
Args
[phase]— default: current active phase[type-filter]— optional, filter by owner_type
Steps
-
Query the tracker — never
plans/phases.yaml— for status or dependencies. Use the Tracker interface (mcp__linear-server__list_issuesfor Linear,gh issue listfor GitHub,ntnfor Notion) to find active issues in the current cycle that are:- Status: Todo (or Backlog with no blockers)
- All
blocked_byissues are Done — verify viarelations.blockedBy(issue prose likeDepends on: forge#Nis unreliable)
phases.yamlis a local execution snapshot derived from the tracker — every status, dependency, or blocker field in it can be stale. The tracker is authoritative for all execution metadata; see your projectCLAUDE.md§Source of truth. -
If multiple match, list and ask user to pick. If one, auto-pick.
-
Set Linear issue status → "In Progress"
-
Compute branch name:
feat/{LINEAR-ID}-{kebab-case-title} -
Create the worktree + hydrate gitignored project meta via the CLI verb:
forge orchestrate ensure-worktree --task "${LINEAR_ID}" --jsonThe verb (
src/cli/orchestrate/ensure-worktree.ts) owns:- Task-ID sanitization (same rules as
src/core/workspace.ts#sanitizeIssueId) - Repo-root resolution via
git rev-parse --git-common-dirso the worktree lands under the main checkout (not a sibling worktree, which would nest) git worktree addat.forge/worktrees/<sanitized-id>/.forge/worktree-task.jsonmarker (binds worktree to task ID for worktree-guard preflight in/implement,/ship,/qa)- Hydration of
spec/*.md,plans/,docs/learnings/,CLAUDE.md,CRITICAL.md, and.forge/settings.yamlfrom the main checkout — these are gitignored as a dogfooding rule but workers need them at runtime - Idempotence: if the worktree already exists with a matching marker, no-op
exit 0; conflicting marker exits 1 with
WORKTREE_CONFLICT
- Task-ID sanitization (same rules as
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 · 171 lines · 34 tokens per session scan C cd80d268992f
pickup-task is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,084 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.