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/jdanigo/hydraianpx agentmods add skills/jdanigo/hydraia/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/jdanigo/hydraia/subagent-driven-development)<a href="https://agentmods.dev/skills/jdanigo/hydraia/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jdanigo/hydraia/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/jdanigo/hydraia/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jdanigo/hydraia/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 | $0.04843 |
| Opus 5.5 | $0.00007 | $0.01937 |
| Sonnet 5.5 | $0.00003 | $0.00969 |
| Haiku 4.5 | $0.00002 | $0.00484 |
Grade A, and why
subagent-driven-development 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.
This is a copy
100% identical to subagent-driven-development — 0 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 — 419 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: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
When to Use
digraph when_to_use {
"Have implementation plan?" [shape=diamond];
"Tasks mostly independent?" [shape=diamond];
"Stay in this session?" [shape=diamond];
"subagent-driven-development" [shape=box];
"executing-plans" [shape=box];
"Manual execution or brainstorm first" [shape=box];
"Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
"Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
"Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
"Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
"Stay in this session?" -> "subagent-driven-development" [label="yes"];
"Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}
What ships with it
5 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.
- 1mo ago First seen · 419 lines · 17 tokens per session scan A 41ab239a6ad1
subagent-driven-development is a skill published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 25d ago), licensed MIT. It adds 17 tokens to every session and 4,843 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to subagent-driven-development, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
pm-tech-spec-review
Review an engineering technical spec through a PM lens — does it cover every PRD requirement, does it preserve user/UX intent, does it quietly add or drop scope, what are the product risks, what's missing for launch. Produces a priority-tagged findings list + clarifying questions for engineering. Use after eng drafts…
review
Use when asked for an opinionated review of the codebase - architecture/backend findings, UI findings against the project's own design docs, or both - severity-ranked with evidence, written to docs/capstone/review.md. Bare "review" does both sides; "review backend" or "review frontend" does one. "review retro…
pr-authoring
Playbook for deployment-aware pull requests — the 11-section format that turns a PR into a reviewable contract; why, decision requested, change map, review order, evidence, verification, risk, rollback. Used for the Define→build handoff and any PR a great-pm-driven project opens.
pr-review
Playbook for reviewing pull requests — verdict format, verification-not-trust, severity-ranked findings with concrete fixes, risk acceptance on the record. The reviewer-side counterpart of pr-authoring.
code-review
Reviewing a diff, branch, or PR for bugs, regressions, missing tests, and merge readiness.
deliver-task
Drive one READY task end-to-end — implement in a worktree, independent adversarial review, bounded 3-iteration patch loop, then hand to a human for merge. Pass the issue number, e.g. "/deliver-task 42". A single-command composition of next-task + review-task + patch-task.