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 skills add firatcand/forge --skill forge-orchestrategit clone --depth 1 https://github.com/firatcand/forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/firatcand/forge/forge-orchestrate)<a href="https://agentmods.dev/skills/firatcand/forge/forge-orchestrate"><img src="https://agentmods.dev/badge/skills/firatcand/forge/forge-orchestrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/firatcand/forge/forge-orchestrate"><img src="https://agentmods.dev/badge/skills/firatcand/forge/forge-orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00071 | $0.03539 |
| Opus 5.5 | $0.00028 | $0.01416 |
| Sonnet 5.5 | $0.00014 | $0.00708 |
| Haiku 4.5 | $0.00007 | $0.00354 |
Grade A, and why
forge-orchestrate 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 1mo 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge orchestrate
Status queries always hit the tracker.
plans/phases.yamlis a stale cache. See your projectCLAUDE.md§Source of truth.
The user-facing dispatch loop for forge's orchestrator. Drives one round per invocation:
- List ready tasks (read-only) → 2. user approves → 3. claim + dispatch the selected tasks → 4. spawn worker subagents via the host's Task tool → 5. poll open questions for that run → 6. surface each to the user → 7. record answers → 8. ask user whether to continue with another round.
No daemon. No automatic dispatch. The skill exits after each round; the user
re-invokes /forge orchestrate to start the next round.
Drift-routed questions, drift_event_id, and routing_hint are dropped in
v0.4 per docs/plans/team-mode-minimum-architecture.md §3. Workers emit
plain questions only; the skill consumes them via questions --open --json.
Preconditions
.forge/settings.yamlexists with atracker:blockplans/phases.yamlexists and validates (run/reconcile --pullfirst if not)templates/worker-prompt.template.mdexists (shipped with the framework)
Step 0 — Start a run
A "run" is a single supervisor session. Every subsequent verb call needs the run_id so questions and dispatch records stay scoped to this session.
forge orchestrate run start --json
Parse data.run_id and keep it in your skill context for the rest of the
invocation. If you need a friendly name, pass --name "<short label>".
Step 1 — List ready tasks (read-only)
forge orchestrate phases --ready --run "${RUN_ID}" --limit 5 --json
Parse data.tasks[]. Each entry has task_id, title, phase, priority,
estimate, depends_on, and an overlap object showing whether the task's
write globs collide with anything already in-flight.
If data.tasks.length === 0, print "No ready tasks." and exit 0.
Step 2 — Ask the user which tasks to dispatch
Use AskUserQuestion (contract: skills/_shared/question-format.md):
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.
- 1mo ago First seen · 305 lines · 71 tokens per session scan A 73b49e3f8319
forge-orchestrate is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 3,539 once invoked, about $0.0003 per session on Opus 5.5. 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-change
Create or advance a lightweight OSpec change using the classic fast workflow.
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…