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/w00fx/spec-anchored-agentic-development/implement-orchestratednpx skills add w00fx/spec-anchored-agentic-development --skill implement-orchestratedgit clone --depth 1 https://github.com/w00fx/spec-anchored-agentic-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/w00fx/spec-anchored-agentic-development/implement-orchestrated)<a href="https://agentmods.dev/skills/w00fx/spec-anchored-agentic-development/implement-orchestrated"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/implement-orchestrated.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 5.1 | $0.00053 | $0.00505 |
| Opus 5 | $0.00026 | $0.00253 |
| Sonnet 5 | $0.00011 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
implement-orchestrated 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 today.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement-orchestrated — orchestrator-owned Owner adapter
First action: read .agents/protocols/implementation-protocol.md. The parent
worker is the Owner. The orchestrator schedules and monitors; it never authors
the code or silently integrates subagent work.
Invocation
implement-orchestrated issue #<N> --mode assisted|autonomous
The issue pins the effective spec and stable IDs. --mode is launcher policy,
not inferred from prose.
Gate and pass providers
| Protocol need | assisted | autonomous |
|---|---|---|
| Ambiguity | Comment exact question/evidence, label, release claim, NAMED_BLOCKER |
Same |
| Plan | Post plan + exact APPROVAL-FINGERPRINT; edit nothing until human replies approved <fingerprint> |
Owner may proceed only for a qualified class whose ticket/spec/policy mechanically determine the plan; any load-bearing decision blocks. No plan-review agent |
| Spec change | SPEC_CHANGE_REQUIRED, proposal-only, release claim |
Same |
| Scope/dependency/schema/data/external-action expansion | Blocker | Blocker |
| General code hardening | Dispatch only general-code-reviewer; Owner inspects and integrates accepted local commit |
Same |
| Mutation hardening | Dispatch only mutation-hardener; Owner inspects and integrates accepted local commit |
Same |
| External specialized reviews | Orchestrator/pipeline may run them after PR; they are not internal agents | Same |
| Delivery | No-change: post corroborated evidence terminal. Code: open PR, post URL/outcome, park for re-engagement | Same |
Owner handoff rule
For both internal agents, record input/output SHA, changed paths, rationale, commands/results and Owner disposition. Reject any truth, scope, gate or permission change. Any Owner correction after mutation hardening reruns both internal passes.
Engine parity
Each worker invokes implement-orchestrated using its runtime's native explicit-skill syntax. The launcher refuses a runtime whose actual skill/agent installation is absent.
What ships with it
2 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.
- today Changed · -8 lines · -21 tokens per session 532b6c0f6ceb
- 5d ago First seen · 56 lines · 74 tokens per session scan A eb39bd1ff30f
implement-orchestrated is a skill published in the GitHub repository w00fx/spec-anchored-agentic-development (5 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 505 once invoked, about $0.0003 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
Accept
The boundary ritual — review what just landed, record an approval, journal it, and advance the phase. The ONLY step that writes approvals, and it does NO git.
A5 — Web Audit
Research the world. Real web research to find what the best teams do for every technology and pattern in the build, then implement superior approaches now (not later). The only lens that brings outside knowledge.
Brainstorm
Interactive ideation and decision capture at any pipeline boundary. Opinionated dialogue that surfaces contradictions, gaps, and untested assumptions — not template-filling. Feeds the Furnace.
Specify
Write the master spec — the WHAT. User stories, functional & non-functional requirements, acceptance criteria, and the dependency-ordered micro-spec plan. Strictly WHAT, never HOW.
A1 — Design & Master-Spec Consistency
The drift check. Compare what was built against the design doc and master spec. Sets the Double Gate — A3 cannot start until A1 is at zero findings.
A3 — Polish
Code/content quality. Dead code, hardcoded values, leftover TODOs, weak error handling, security holes, performance traps, standards violations. Enforces the Double Gate — blocks until A1 is at zero findings.