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 lttr/claude-marketplace --skill implement-specgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/implement-spec)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/implement-spec"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/implement-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/lttr/claude-marketplace/implement-spec"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/implement-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 | $0.00032 | $0.03052 |
| Opus 5 | $0.00016 | $0.01526 |
| Sonnet 5 | $0.00006 | $0.00610 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
implement-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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow at a glance
- Resolve input: find the task folder and its tickets. Nothing there → stop
- [GATE] spec concrete enough? Last chance to ask the user. Past this, unattended
- Task worktree: own branch, the whole run happens there. User's checkout stays untouched
- [LOOP] repeat until every ticket is done:
- pick the ready tickets: those whose blockers are all done
- run one implementer subagent per ready ticket, in parallel, each in its own worktree
- inside each: implement with tests → run the checks → simplify → verify criteria → done → commit
- as each returns, land its work onto the task branch one at a time (linear history), keep its notes, drop its worktree
- landed work may unblock more tickets → next round. A ticket that cannot be finished stops the whole run
- Wrap-up (once): full project verification on the merged branch
- Fresh-context review of the whole diff, fixes applied, outcome saved as the review record
- Clean up and report: remove leftover worktrees and branches, tell the user what's done and where the branch is
Follows the aiwork-protocol skill. Don't enter plan mode: the spec and tickets are the plan.
1. Resolve input
$ARGUMENTS is a spec/PRD or task folder path. With no args, find the most recently modified task folder (per aiwork-protocol conventions). Resolve it to an absolute path and use that everywhere, including in subagent prompts. Locate the tickets/ subfolder:
- No tickets → suggest
/to-tickets, or/implement <spec>if the spec is small enough for one pass. Stop. - All tickets
donebut noreview.md→ go straight to Wrap-up (§5). - Nothing found → tell the user and stop.
2. Clarity gate
Before touching code, check the spec is concrete enough for an unattended run. Warn and stop for confirmation if any hold:
- Open questions, TBDs, or unresolved decisions
- Key technical choices (data model, API shape, file targets) unspecified
- Success criteria too vague to tell when "done"
- Content is contradictory, out of order, or otherwise corrupted
- An external service or credential the tickets depend on is unreachable or unset
- The spec has an Open Concerns section with anything in it
- The task folder has an
intent.mdwhosestatusis notaccepted
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.
- yesterday Changed · +2 lines 33405adbe4c9
- 3d ago Changed · +36 lines d04b2e3e20e9
- 8d ago First seen · 100 lines · 32 tokens per session scan A 2b20d27b8cc7
implement-spec is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 3,052 once invoked, about $0.0002 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
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
hook-factory
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.