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 davidYichengWei/Agency --skill planninggit clone --depth 1 https://github.com/davidYichengWei/AgencyWrote 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/davidyichengwei/agency/planning)<a href="https://agentmods.dev/skills/davidyichengwei/agency/planning"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/planning/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/davidyichengwei/agency/planning"><img src="https://agentmods.dev/badge/skills/davidyichengwei/agency/planning.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 | $0.00219 | $0.01456 |
| Opus 5 | $0.00110 | $0.00728 |
| Sonnet 5 | $0.00044 | $0.00291 |
| Haiku 4.5 | $0.00022 | $0.00146 |
Grade A, and why
planning 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning
When to plan
Create a plan when the task involves multiple steps that span more than one quality gate:
- New feature (requirements → design → implement → test → review → submit) — yes
- Bug fix with investigation needed — yes
- Significant refactor across modules — yes
- Performance optimization (profile → optimize → benchmark) — yes
- Simple config change, one-line fix, quick code review — no, just do it
When in doubt, create a plan — the overhead is small and the crash recovery benefit is significant.
Creating a plan
- Research the codebase to understand scope and complexity
- Copy
assets/plan-template.mdto.agent/<task-name>/plan.md - Fill in: goal, success criteria, steps
- Present the plan at Gate: Requirements Understanding for user approval
- After approval, start executing — you drive the process
Following a plan
- Always know which step you're on. Mark
[~]when starting a step,[x]when done. - After the user approves at a quality gate, continue to the next step autonomously.
- If you lose track (e.g., after context compaction), re-read
plan.mdandactivity.mdto reconstruct where you are.
Revising a plan
The plan is a living document. Update it when:
| Situation | What to do |
|---|---|
| Scope expands during a task | Update the existing plan — add steps, revise goal/success criteria. Do NOT create a second plan for overlapping work. |
| Approach changes after a gate | Update the remaining steps. Mark outdated steps as skipped with rationale. |
| Task naturally splits into independent work streams | Split into separate .agent/<task>/ directories, close the original. |
| User gives a completely new, unrelated task | New .agent/<new-task>/plan.md. |
| Previous task's plan is stale/superseded | Mark it complete or delete it. |
One task directory = one plan = one coherent work stream. Never have two active plans for overlapping work. If a new plan subsumes an old one, close the old directory.
Feature Development: the canonical step sequence
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 66 lines · 219 tokens per session scan A 8a932ec69b2a
planning is a skill published in the GitHub repository davidYichengWei/Agency (5 stars, last pushed 4mo ago), licensed MIT. It adds 219 tokens to every session and 1,456 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…