Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ForgeyClap/claude-forgenpx agentmods add skills/forgeyclap/claude-forge/subagent-driven-developmentWrote 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/forgeyclap/claude-forge/subagent-driven-development)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/subagent-driven-development/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/forgeyclap/claude-forge/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/subagent-driven-development.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 | $0.00017 | $0.07688 |
| Opus 5.5 | $0.00007 | $0.03075 |
| Sonnet 5.5 | $0.00003 | $0.01538 |
| Haiku 4.5 | $0.00002 | $0.00769 |
Grade C, and why
subagent-driven-development 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 20d 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.
delete this plan's workspace (`rm -rf <workspace>`) — the git history is This is a copy
94% identical to subagent-driven-development — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent-Driven Development
Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.
Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
Core principle: Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration
Narration: between tool calls, narrate at most one short line — the ledger and the tool results carry the record.
Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
Rulings, not stalls. A running plan does not wait on a human. Conflicts,
ambiguities, plan defects, a cap you would have asked to exceed — decide
them. The spec is the binding authority, the plan is its argument, and your
judgment settles what neither answers. Record every decision in the ledger as
Ruling: <what you decided> — <why> — <what it costs if wrong>, and keep
going. A wrong ruling costs rework your human partner can see and undo; a
session parked on a question costs their whole day and buys nothing.
Four things stop you, and only these: an irreversible or destructive operation; a security-sensitive action; a side effect outside this worktree that norms say you ask about first (a merge, a push to a shared branch, a publish); and a plan so broken that every path forward is a guess. For those, stop and ask.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago First seen · 579 lines · 17 tokens per session scan C 3a47d9f91192
subagent-driven-development is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 15d ago), licensed MIT. It adds 17 tokens to every session and 7,688 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 94% identical to subagent-driven-development, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
validate
Use when operating as the Fabrik Validate stage agent. This skill guides final validation of an implementation, verifying requirements are met, tests pass, and the PR is ready to merge.
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.
pr-comments
Triage unresolved review threads on an open PR: per thread either agree (fix, verify, push, reply, resolve) or disagree (justify with a version-matched citation). Use when asked about PR comments or told to reply and resolve.
orchestrate
Run the review lenses over a change: pick the ones the change touches, read or dispatch each, gate go/no-go on cited evidence. Use when asked for our lenses, or to plan or verify a non-trivial change.
pr
Write or draft a minimal GitHub PR title and body: a linked tracker close line plus 3 to 6 one-line bullets, nothing else. Use when running gh pr create / gh pr edit or when asked for a PR description.