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/codagent-ai/agent-skills/implement-changenpx skills add Codagent-AI/agent-skills --skill implement-changegit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWhat 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 | $0.00066 | $0.00687 |
| Opus 5 | $0.00033 | $0.00344 |
| Sonnet 5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
implement-change 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Act as the tech lead for this work, overseeing implementor subagents who do the coding while remaining responsible for the successful completion of the deliverable.
Review all provided tasks and context (design docs, specs, proposals, etc.) before starting — understanding the full scope upfront prevents costly mid-implementation surprises and ensures each subagent receives the right context. If anything is ambiguous or missing, ask before starting.
Execution
Complete all tasks and get to a merged PR without requiring user intervention. Do not stop to ask permission, confirm next steps, or check in between tasks — make decisions and keep moving. The only valid reason to pause is a genuine blocker that cannot be resolved independently; in that case, surface it clearly and wait for guidance.
Step 1: Implement tasks
Identify all incomplete tasks from the provided task list.
Implement each task by invoking codagent:implement-and-validate as a subagent, one at a time.
Pass the full task description along with all relevant context provided.
Tasks run sequentially rather than in parallel because each one typically builds on the previous — parallel execution risks conflicts, ordering issues, and subagents stepping on each other's work. Wait for each subagent to complete and review its report before moving to the next task.
If a subagent reports failure, check the failure report for the root cause:
- Missing context or clarification needed: Provide the additional information and re-invoke the subagent.
- Retry limit exceeded after multiple attempts: Review the failure details. If you can address the root cause (e.g., environment setup, a prerequisite task that wasn't complete), fix it and re-invoke once. Otherwise, surface it to the user.
- Immediate blocker (contradictory requirements, missing dependency): Surface to the user immediately with the full blocker details.
Mark each task complete before moving on.
Step 2: Run validator
Run agent-validator detect 2>&1 and branch on the exit code:
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 · 59 lines · 66 tokens per session scan A b27e624e2403
implement-change is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 687 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
organize-project
Organise documents into folders and move them between folders and modules with MOVE. Use when a module has grown unstructured, when restructuring a project, or when a document is in the wrong place.
smithers-supervise
Watch for stale running runs and auto-resume them. Run smithers supervise --help for usage details.