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-backlog/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-backlog)<a href="https://agentmods.dev/skills/w00fx/spec-anchored-agentic-development/implement-backlog"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/implement-backlog.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 | $0.00060 | $0.00505 |
| Opus 5 | $0.00030 | $0.00253 |
| Sonnet 5 | $0.00012 | $0.00101 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
implement-backlog 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 2d 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.
What it actually says
implement-backlog — unattended Owner adapter
First action: read .agents/protocols/implementation-protocol.md. No human
answers mid-run. The parent worker is the Owner and must inspect every returned
subagent diff before integrating it.
Mode identity
Invoke implement-backlog issue #<N> with the runtime's native explicit-skill syntax as the launcher's first user message. One qualified issue, one worktree/branch, at most one PR. New
capabilities, semantic invention, broad architecture, and truth/oracle changes
are out of scope.
Gate and pass providers
| Protocol need | Provider in this mode |
|---|---|
| Ambiguity / load-bearing decision | NAMED_BLOCKER with exact question/evidence; never guess |
| Plan | Owner writes a plan only when the qualified ticket, effective spec, repository policy and deterministic oracle fully determine it. Any unpinned decision aborts; there is no plan-review agent |
| Spec change | SPEC_CHANGE_REQUIRED; proposal/comment only; never edit semantics |
| Scope/dependency/schema/data/external-action expansion | Blocker, always |
| General code hardening | general-code-reviewer; Owner inspects exact commit/report, scope and semantics before integrating |
| Mutation hardening | mutation-hardener; Owner inspects exact commit/report and requires the 100% eligible-target contract |
| External specialized reviews | Outside this run; separate monitor/pipeline/human owns them |
| Delivery | Open PR, post link/outcome, terminal PR_READY_AWAITING_HUMAN; never monitor or claim merge |
If either authoring agent returns a semantic/scope/oracle/dependency decision that the unattended policy cannot authorize, abort upstream. A subagent commit is never auto-cherry-picked without the Owner's recorded inspection.
Loop discipline
One issue per run. Release the claim on any blocker. Stop repeated non-progressing attempts and preserve commands, outputs, agent handoffs, Owner dispositions, and cost in the log.
What ships with it
3 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.
- 2d ago Changed · -3 lines · -19 tokens per session 91a129553faa
- 7d ago First seen · 48 lines · 79 tokens per session scan A 0c3adafa8a08
implement-backlog is a skill published in the GitHub repository w00fx/spec-anchored-agentic-development (5 stars, last pushed 4d ago), licensed MIT. It adds 60 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
Status
Pipeline dashboard — current feature, position, per-group progress, approvals, pending PRs, blockers. Read-only, any time.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
gsd-onboard
Guide existing codebase onboarding through mapping, doc ingest, and planning setup.
gsd-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments.