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 skills add donnfelker/loop-skills --skill implement-full-specgit clone --depth 1 https://github.com/donnfelker/loop-skillsWrote 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/donnfelker/loop-skills/implement-full-spec)<a href="https://agentmods.dev/skills/donnfelker/loop-skills/implement-full-spec"><img src="https://agentmods.dev/badge/skills/donnfelker/loop-skills/implement-full-spec/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/donnfelker/loop-skills/implement-full-spec"><img src="https://agentmods.dev/badge/skills/donnfelker/loop-skills/implement-full-spec.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 | $0.00196 | $0.03183 |
| Opus 5.5 | $0.00078 | $0.01273 |
| Sonnet 5.5 | $0.00039 | $0.00637 |
| Haiku 4.5 | $0.00020 | $0.00318 |
Grade A, and why
implement-full-spec 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Full Spec
This skill turns a parent ticket (audit, RFC, multi-finding report, etc.) with N actionable subtasks into a clean stack of N pull requests — and then keeps driving that stack to merge-ready by addressing every comment and review on every PR until reviewers are satisfied. It is the durable version of the workflow proven out on a real multi-finding security audit (24 P1/P2/P3 findings → 24 stacked PRs → multi-round bot review-response cycle).
Dependencies — check these first
This skill orchestrates two skills that ship as separate plugins. Before Phase B, confirm both are installed and invocable:
dev-team(plugin:dev-team) — the per-subtask Dev → QA → Reviewer → commit loop that Phase B runs once per subtask.pr-autopilot(plugin:pr-autopilot) — owns the single-PR review mechanics that Phase C delegates to.
If either /dev-team or /pr-autopilot is unavailable, stop and tell the operator to install the missing plugin(s) from the same marketplace — e.g. /plugin install dev-team and /plugin install pr-autopilot — then re-run. Do not reimplement those loops inline.
When to use this skill
Triggers when the operator points at a parent containing multiple actionable subtasks AND wants each subtask to land as its own PR. Common phrasings:
- "Work through all the P1/P2/P3 subtasks of this ClickUp/Linear/Jira ticket and create a PR for each."
- "Fix all the findings in this audit. One PR per finding, stacked."
- "Use agent teams to fix all the subtasks of [parent]."
- "Address all the comments and bot reviews on PRs #N..#M."
- "Go through these stacked PRs and respond to every review."
- "Drive these to merge-ready. Re-request review when each one is updated."
It is the right skill when all three are true:
- The work is naturally a sequence of small, independently-reviewable units (≥3, typically 5–30).
- Subtasks share enough surface that stacked branches are cheaper than 30 branches off main.
- The user wants the orchestration to outlast a single attention span — fold in clarifications, hit review feedback, request re-review.
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 · 153 lines · 196 tokens per session scan A b7d73f6881f5
implement-full-spec is a skill published in the GitHub repository donnfelker/loop-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 196 tokens to every session and 3,183 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
cuga-github-issues
Create GitHub issues for cuga-agent (bugs, features, epics, designs, and related work) against origin using gh, with epic → feature → issue hierarchy and GraphQL sub-issue linking. Use when the user says create new issues, report a bug, file a bug, feature request, new feature, create an epic, GitHub issue, sub-issue…