Borrowing it
Nothing to install: this file belongs to w00fx/spec-anchored-agentic-development. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/w00fx/spec-anchored-agentic-development/main/.agents/skills/implement-feature/SKILL.mdgit 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-feature)<a href="https://agentmods.dev/skills/w00fx/spec-anchored-agentic-development/implement-feature"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/implement-feature/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/w00fx/spec-anchored-agentic-development/implement-feature"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/implement-feature.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 | $0.00062 | $0.00754 |
| Opus 5.5 | $0.00025 | $0.00302 |
| Sonnet 5.5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
implement-feature 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement-feature — supervised Owner adapter
First action: read .agents/protocols/implementation-protocol.md. It is the
complete state machine. This adapter only names the providers for supervised
work.
Mode identity
Invoke implement-feature <issue | spec slice | task> using the runtime's native explicit-skill syntax. The human
is present in-session. Never launch this skill headlessly; use
implement-backlog for unattended work and implement-orchestrated for an
orchestrator-owned worker.
The parent agent is the Owner. The Owner alone talks to the human, owns the branch/run terminal, and decides whether to integrate commits returned by the two internal agents.
Gate and pass providers
| Protocol need | Provider in this mode |
|---|---|
| Ambiguity / unauthorized assumption | Human in-session after repository research; present numbered options and a recommendation |
| Plan, scope, evidence, mutation/fuzz applicability | Human approval of the exact APPROVAL-FINGERPRINT |
| Semantic spec amendment | Human in-session; affected IDs, old → proposed meaning, rationale and verification delta; PR merge ratifies |
| Scope/dependency/schema/data/external-action expansion | Human approval of a new scope + fingerprint |
| General code hardening (Phase 7) | Dispatch only general-code-reviewer. It edits in an isolated worktree and returns a local commit + full change report. Owner inspects and accepts/rejects before integration |
| Mutation hardening (Phase 8) | Dispatch only mutation-hardener. It may edit production/tests to reach the 100% target contract and returns a local commit + mutation report. Owner inspects and accepts/rejects before integration |
| External specialized reviews | Outside this skill. The PR/pipeline/orchestrator may run spec, conformance, security, performance, compliance, architecture, or independent code review |
| Delivery | PR opened; human reviews/merges. Terminal PR_READY_AWAITING_HUMAN |
Agent call graph
Owner implementation
→ deterministic baseline
→ general-code-reviewer [internal authoring loop]
→ Owner diff review + integration
→ mutation-hardener [internal authoring loop to 100%]
→ Owner diff review + integration
→ final deterministic verification
→ PR / external review pipeline
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.
- 1mo ago Changed · +6 lines · -3 tokens per session 9f331c1240de
- 1mo ago First seen · 65 lines · 65 tokens per session scan A 3f9f996e2c36
implement-feature is a skill published in the GitHub repository w00fx/spec-anchored-agentic-development (7 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 754 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
code-simplifier
Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why.
critical-review
4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and [VALIDATION] report.
agent-delegation
Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context.
memory-first
Lookup chain enforced before any file read or search: project and global memory, grep/glob, targeted read — stop at the first step that answers.
verbosity
Response verbosity protocol: reads the level from /.claude/memory/verbosity.md and applies the MIN, INFO or VERBOSE output rules to every reply.
project-bootstrap
A workflow for adapting the smyslokod-starter project template to a specific product idea. It chooses a depth of setup and uses the template's business and project files as starting context.