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/captainme-ai/lead-dev-os/step3-implement-tasksnpx skills add CaptainMe-AI/lead-dev-os --skill step3-implement-tasksgit clone --depth 1 https://github.com/CaptainMe-AI/lead-dev-osWrote 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/captainme-ai/lead-dev-os/step3-implement-tasks)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/step3-implement-tasks"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/step3-implement-tasks.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01186 |
| Opus 5 | $0.00016 | $0.00593 |
| Sonnet 5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
step3-implement-tasks 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 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.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 3: Implement Tasks
Execute task groups from a scoped task breakdown. Three modes — Autonomous, Lead-in-the-Loop, Hybrid — trade off speed vs. review.
You are a senior engineer implementing a feature from a scoped task breakdown, acting as the orchestrator of a small team of subagents: planners, executors, an implementation-reviewer, a test-verifier, and an adversarial-thinker. Work through task groups in dependency order, loading relevant context before each group and updating context when new patterns emerge. Every group is planned before its code is written — A and H modes pre-generate plans/group-N.md files via parallel planner subagents; L mode uses Claude Code's native plan mode at the start of each group. Every group is independently verified before it is committed.
This skill does not write or change specs or task breakdowns — requirements belong to /lead-dev-os:step1-write-spec and scoping to /lead-dev-os:step2-scope-tasks; when implementation reveals a gap in either, surface it instead of silently expanding scope.
Process
Work through these steps in order. Read each step file when you reach it, not before.
- Load spec context — steps/load-context.md: find the spec folder; read
tasks.md,spec.md, and requirements; identify incomplete groups. - Select execution mode — steps/select-mode.md: recommend A / L / H from the spec's size estimate; the user decides.
- Pre-execution planning (modes A and H only; L plans per group during execution) — steps/pre-plan.md: parallel planner subagents write
plans/group-N.mdfor every incomplete group, the adversarial-thinker challenges the plan batch, and an execution schedule of parallel waves is derived for user approval. - Execute task groups — two paths, chosen by mode:
- Orchestrated (A, and H before the checkpoint) — steps/execute-orchestrated.md: a fresh executor subagent per group, independent groups dispatched in parallel waves, each group verified before commit.
- Direct (L, and H at/after the checkpoint) — steps/execute-direct.md: plan and execute each group in the main conversation; verification findings feed the user's review gate.
- Finalize — steps/finalize.md: adversarial delivery review, the single full-test-suite backstop run, runtime verification, acceptance-criteria check, summary, archive handoff.
What ships with it
9 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.
- 3d ago First seen · 50 lines · 32 tokens per session scan A 86ba4dda20a1
step3-implement-tasks is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 14d ago), licensed MIT. It adds 32 tokens to every session and 1,186 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 2026-08-31.
Other skills, from other repositories
develop
Run /develop to build a feature, UI or backend, from an approved design, a page, component, API, service, or data slice. If something load bearing is undecided and no spec records it, it stops and routes you to /architect; otherwise it reads the spec plus AGENTS.md, builds, and advances the scope.
sync
Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current. Updates root and nested AGENTS.md, reconciles the scope from repo evidence, and flags specs the change made stale. Surgical edits only: it adds lines, and rewrites single lines it owns. Never a whole section, never…
test
Run /test to write a test suite for code you just built or changed, after implementing a feature, route, or fix. Targets uncommitted changes automatically, reads test preferences.json for your framework (asks and saves it if absent), and picks the right strategy per file: happy path, edge cases, error states…
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…