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 qinghaoliqaq/AutoCoder --skill spec_driven_implementationgit clone --depth 1 https://github.com/qinghaoliqaq/AutoCoderWrote 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/qinghaoliqaq/autocoder/spec_driven_implementation)<a href="https://agentmods.dev/skills/qinghaoliqaq/autocoder/spec_driven_implementation"><img src="https://agentmods.dev/badge/skills/qinghaoliqaq/autocoder/spec_driven_implementation/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/qinghaoliqaq/autocoder/spec_driven_implementation"><img src="https://agentmods.dev/badge/skills/qinghaoliqaq/autocoder/spec_driven_implementation.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 | $0.00069 | $0.01015 |
| Opus 5.5 | $0.00028 | $0.00406 |
| Sonnet 5.5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
spec-driven-implementation 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Implementation
This skill is the entrypoint for the spec-driven workflow. It does not write code or specs itself — it sequences other skills and enforces the gates between them.
When To Use
Use when:
- The task is large enough that diving straight into code would risk rework (touches 3+ modules, has architectural choices, or affects shared infrastructure)
- The user explicitly asks for "spec-driven", "with a spec", or references the workflow by name
- You're unsure whether to spec or just code — err on the side of spec'ing if a wrong implementation would cost more than 30 minutes to redo
Don't use for:
- One-line fixes / typo corrections
- Routine refactors with obvious scope
- Exploration ("just look at how X works") — use direct tool calls
The Three Phases
Phase 1 — Spec
Invoke the write-tech-spec skill (via the Skill tool, or by
following its instructions inline if you've already loaded it).
Outcome: specs/<id>/TECH.md exists with all required sections,
file:line citations verified, and 80–150 lines.
Phase gate: stop and surface the spec to the user before implementing. Do this by:
- Telling the user where the spec was written.
- Highlighting the most important Risks & Open Questions.
- Asking via
AskUserQuestionwhether to proceed, revise, or abandon.
If the user requests revisions, loop back to write-tech-spec with
their feedback as additional input. Do NOT silently proceed to Phase 2
without explicit go-ahead.
Phase 2 — Implement
Invoke the implement-specs skill against the now-approved spec.
Outcome: code changes committed in step-sized commits, spec updated in the same commits whenever the implementation diverges from what the spec proposed, optional PROJECT_LOG.md / DECISIONS.md maintained.
Phase 3 — Verify & Document
After the last Implementation Plan step:
- Run the full test scenarios in TECH.md's Testing section.
- Invoke the
verifyskill for a build / test sanity sweep. - Append a final PROJECT_LOG.md entry: "spec landed, PRs: …".
- Confirm TECH.md's Current State now describes the new state, not the pre-change state.
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 · 113 lines · 69 tokens per session scan A bcfe561ac57b
spec-driven-implementation is a skill published in the GitHub repository qinghaoliqaq/AutoCoder (12 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,015 once invoked, about $0.0003 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
multi-agent
Run work across more than one agent — the task subagent, the delegate tool, background commands, and the user's other live agentica sessions reached with listagents / sendmessage (including a second CLI in tmux). Use when a job wants parallel workers, when choosing among these, or when coordinating with or answering…
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
werewolf-6p
Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
pptx
Instructions for reading, creating, and editing PowerPoint presentation files and templates, including .pptx, .potx, and older .ppt files. They cover text, tables, images, charts, layouts, and speaker notes.