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 agentmods add skills/conn-castle/agent-layer/implementnpx skills add conn-castle/agent-layer --skill implementgit clone --depth 1 https://github.com/conn-castle/agent-layerWhat 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 | $0.00027 | $0.00843 |
| Opus 5 | $0.00014 | $0.00421 |
| Sonnet 5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
implement 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement
Inputs
Require a task, request, or spec as <input> and dispatch targets named
implementer, plan_reviewers, and code_reviewer. Providing a target does
not imply its use. Do not infer missing targets. Use /dispatch-agent for every
dispatch.
Decide Implementation Approach
Inspect the relevant architecture. Reuse existing code and established patterns
when they fit <input>. Resolve substantive requirements and tradeoffs before
implementation.
Planning and independent review add significant cost. Before implementation, answer each question yes or no:
- Is a written plan required to confidently complete and verify
<input>? - If a plan is required, does its material risk or complexity justify independent plan review?
- Does the implementation's material risk or complexity justify independent code review, whether implementation is direct or planned?
If no plan is required, implement <input> directly without dispatching or
writing a plan. Run only targeted checks as needed. Check completion against
<input>, resolve gaps until implementation is complete. Then continue to
the Finish section.
Implementation with a Written Plan
If a plan is required, write the following self-contained artifacts. Set
<run-id> to YYYYMMDD-HHMMSS-<short-rand>:
.agent-layer/tmp/write-plan.<run-id>.plan.md- the implementation plan.agent-layer/tmp/write-plan.<run-id>.task.md- a checklist for all requirements, used to assess completion.agent-layer/tmp/write-plan.<run-id>.context.md- all background and context required for executing the implementation plan
If independent plan review is required, write each reviewer a self-contained
prompt instructing it to review the plan artifacts against <input> without
editing files or implementing. Dispatch all plan_reviewers concurrently. Then
update the artifacts to address any findings you agree with that are within
<input>'s scope. Do not repeat plan review.
Finally, dispatch implementer with a prompt instructing it to implement the
plan from the artifacts, run only targeted checks as needed, and return only
after completing the plan. The prompt must also instruct it not to invoke the
implement skill or dispatch another implementer.
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 First seen · 90 lines · 27 tokens per session scan A 2f80cb012bf3
implement is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 843 once invoked, about $0.0001 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
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.