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 jellydn/my-ai-tools --skill implement-specgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/implement-spec)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/implement-spec"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/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/jellydn/my-ai-tools/implement-spec"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/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 | $0.00020 | $0.01341 |
| Opus 5.5 | $0.00008 | $0.00536 |
| Sonnet 5.5 | $0.00004 | $0.00268 |
| Haiku 4.5 | $0.00002 | $0.00134 |
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 10d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Spec
Build a complete specification from its dependency-aware ticket graph. The goal is a verified integration branch, not a collection of disconnected worker branches.
When to Use
Use when:
- A reviewed spec exists.
- Tickets describe acceptance criteria and blocking relationships.
- The user wants the whole spec implemented rather than one ticket.
Do not use when the spec is still ambiguous, tickets are missing dependencies, or the user only wants one isolated ticket. Resolve those inputs first with the relevant planning skills.
Contract
Before changing code, identify:
- The spec path or authoritative issue/plan.
- The ticket source and ticket status format.
- The dependency field used to define blocking relationships.
- The repository's test, lint, typecheck, and build commands.
- The base branch and the requested integration branch name.
If any of these cannot be found, stop and report the missing input instead of inventing a task graph.
Workflow
1. Read the graph once
Read the full spec and all tickets. Extract a compact work map:
Ticket Blocks on Files/area Acceptance check Status
TICKET-1 none parser unit test ready
TICKET-2 TICKET-1 API integration test blocked
A ticket is on the frontier when every blocker is complete. Tickets are not a serial to-do list: independent frontier tickets may run concurrently.
2. Explore before parallel work
Use one exploration pass, or a dedicated exploration worker, to locate existing patterns, ownership boundaries, relevant tests, and external documentation. Save substantial findings in a temporary notes directory accessible to later workers. Do not make every implementer rediscover the repository.
3. Create the integration branch
Start from the latest remote base and create one integration branch. Keep it separate from the default branch. Do not open a PR unless the user asks, the issue tracker requires it to close tickets, or the workflow explicitly says to do so.
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.
- 10d ago First seen · 147 lines · 20 tokens per session scan A d03c90c86fb3
implement-spec is a skill published in the GitHub repository jellydn/my-ai-tools (123 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 1,341 once invoked, about $0.0001 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 2026-10-07.
Other skills, from other repositories
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
factory-recover
Experimental workflow for finding and resuming interrupted coding runs. Use after an agent host restart or an interrupted automation.
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
db-repo
A command for working with a 1C configuration repository, which stores versions and controls changes to configuration objects.