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/lucasduys/forge/collaboratingnpx skills add LucasDuys/forge --skill collaboratinggit clone --depth 1 https://github.com/LucasDuys/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 | $0.00037 | $0.03074 |
| Opus 5 | $0.00018 | $0.01537 |
| Sonnet 5 | $0.00007 | $0.00615 |
| Haiku 4.5 | $0.00004 | $0.00307 |
Grade A, and why
collaborating 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborating Skill
You are driving /forge:collaborate. The primitives live in
scripts/forge-collab.cjs (exported by require into a local Node script
or invoked via node -e). This skill translates user intent into calls
against those primitives, honoring the invariants from spec-collab:
- Session ID is derived from
git remote get-url origin; all participants in the same repo auto-join the same session. - During the
executingphase, AI decisions never block humans: they become flags that humans can review and override async. - Writes to shared coordination state (consolidated.md, categories.json)
are gated by a short-lived
consolidationlease to prevent concurrent overwrites. - All brainstorm + consolidated + categories + questions + flags
artifacts live under
.forge/collab/and are committed to git so late joiners get full context viagit pull.
Subcommand Dispatch
Read the first word of the user's arguments. Route to the matching phase
below. If no subcommand is given, default to status.
start -- initialize a session
-
Derive the session ID by calling
sessionIdFromOrigin()via a small inline Node script:node -e "console.log(require('./scripts/forge-collab.cjs').sessionIdFromOrigin())"If this throws because there is no
originremote, tell the user to add one and stop. -
Resolve the participant handle: prefer
gh api user --jq .login, fall back togit config user.email, finally$USER. -
Ensure
.forge/collab/exists (mkdir -p .forge/collab). -
Write
.forge/collab/participant.jsonwith{handle, session_id, started: <iso>}. Write this FIRST; it is the heavy artifact that holds the session metadata. -
Write
.forge/collab/.enabledas an empty marker file. This MUST be the final filesystem action; it is the atomic signal that collab mode is fully on. Use thewriteEnabledMarkerprimitive:node -e "require('./scripts/forge-collab.cjs').writeEnabledMarker('.forge')"Invariant: if
startcrashes between step 4 and step 5, crash recovery will classify the state asstale_participantand offer a reset. If it crashes before step 4 there is nothing to recover. Do not reorder.
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 · 300 lines · 37 tokens per session scan A 5d8af32c47f2
collaborating is a skill published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,074 once invoked, about $0.0002 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
team-workflow
Design the team's operating rhythm — task management, collaboration rituals, and tooling. Use when the day-to-day cadence needs structure. For a time-boxed sprint, use design-sprint-plan.
github
Triage and orient GitHub repository, pull request, and issue work through the connected GitHub app. Use when the user asks for general GitHub help, wants PR or issue summaries, or needs repository context before choosing a more specific GitHub workflow.
linear
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
backlog-goal
Goal-driven autonomous workflow on top of the backlog CLI. Two strict modes — PREP (exhaustive intake, classify the goal shape, decompose into checkpoints + Scout/Judge/Worker tasks, seed the backlog project, stop) and RUN (execute the board, one active task at a time, structured receipts as comments, Worker tasks…
backlog-loop
Pick up one task from a backlog project and iterate on it until a Judge sub-agent verifies it is genuinely done, then exit. The "loop" is internal to a single task — implement, verify, judge, fix, re-judge — not across multiple tasks. Invoke as /backlog-loop to pull the next highest-priority todo task, or…
backlog
Interact with the Backlog CLI — create and manage tasks, plans, comments, labels, projects, memory, docs, and attachments in a local SQLite workspace.