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/tmj-90/gaffer/plan-changenpx skills add tmj-90/gaffer --skill plan-changegit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/plan-change)<a href="https://agentmods.dev/skills/tmj-90/gaffer/plan-change"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/plan-change.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.01067 |
| Opus 5 | $0.00051 | $0.00534 |
| Sonnet 5 | $0.00020 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00107 |
Grade A, and why
plan-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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan the change before writing code
Implementing without a plan is how a ticket drifts: you discover scope mid-edit, touch files the ticket never asked about, and finish with a diff no one can map back to the ACs. A short, written plan fixes the target before you move — you commit to a scope and a verification path, then execute against it (and later self-review against it).
The plan is a tool, not a deliverable. Keep it tight: a few lines per AC, not a design doc. Its only job is to make scope and proof explicit before the first edit.
Steps
- Re-read the ticket and its ACs. Call
get_ticket(Dispatch MCP). The acceptance criteria — not your sense of the task — define what "done" means. Hold each one. - Consult memory so the plan respects conventions. Call
search_lore(Memory MCP) for relevant conventions, ADRs, test commands, naming rules, and ownership boundaries. A plan that ignores an existing convention produces a correct-but-rejected PR. - Map each AC to a concrete change. For every acceptance criterion, write a line or two:
- which files you will edit or add (real paths — locate them now, not mid-edit);
- what the edit is in one phrase (the actual change, not "implement the feature");
- what test proves it — the specific test you'll add or run, and the command that runs it. Every AC needs a verification path before you start, not after.
- Name what's out of scope — explicitly. List the tempting-but-excluded: refactors the ticket doesn't need, adjacent bugs, files you will not touch. This is the line you hold during implementation and check at self-review. If an AC has no clear in-scope change, that's a gap to clarify — don't paper over it.
- Sanity-check the plan against the ACs. Does executing it satisfy every AC? Is any AC unaddressed, or any planned change unmapped to an AC? Tighten until the plan and the ACs line up one-to-one.
- Output the plan, then execute it. State it briefly (per-AC change + proof, plus the
out-of-scope list) and proceed to
create-branch→ implement. Keep the plan to hand —self-reviewchecks the finished diff against it.
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.
- 4d ago First seen · 67 lines · 102 tokens per session scan A 0e59c9f13b0d
plan-change is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,067 once invoked, about $0.0005 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
skill-creator
Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update an existing skill) that extends AnkaLoop's capabilities with specialized knowledge, workflows, or tool integrations.
ai-engineer
Expert knowledge in AI/ML development, model deployment, and MLOps practices.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志,提供结构化的故障诊断和报告.
security-best-practices
Security best practices and vulnerability prevention guidelines.
react-developer
Expert knowledge in React development, hooks, state management, and modern React patterns.
gh-pr-review
Review GitHub Pull Requests using the gh CLI. Use when a user asks to review a PR, perform code review, check a pull request, or provide feedback on proposed changes. Triggers on phrases like "review PR", "review pull request", "check PR", "code review".