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 phuonghx/aim-cli --skill plan-writinggit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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/phuonghx/aim-cli/plan-writing)<a href="https://agentmods.dev/skills/phuonghx/aim-cli/plan-writing"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/plan-writing/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/phuonghx/aim-cli/plan-writing"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/plan-writing.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 | $0.00087 | $0.01054 |
| Opus 5.5 | $0.00035 | $0.00422 |
| Sonnet 5.5 | $0.00017 | $0.00211 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
plan-writing scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| "Test the endpoint" | "`curl localhost:3000/api/orders` returns 200 with a JSON array" | How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
A good plan is a thinking tool, not paperwork. It exists to make the next actions obvious and to tell you when you are finished. Each plan is shaped to its task -- there is no master template to fill in.
What makes a task good
- Bite-sized. A step should be completable in a couple of minutes and produce one clear result.
- Checkable. You should be able to say exactly how you would confirm it worked -- a command to run, output to see, a value to inspect.
- Ordered sensibly. Note what depends on what, run independent steps in parallel, and call out the critical path. The verification step always comes last.
Where the file lives
Save the plan in the project root as {task-slug}.md, with the slug pulled from the task itself -- "add billing webhooks" becomes billing-webhooks.md. Do not bury it in .aim-agents/, docs/, or a scratch directory.
Five habits to keep
These are habits, not boilerplate. Every plan is unique to its task.
Keep it short
A handful of meaningful steps beats an exhaustive tree of sub-sub-tasks. List only things you will actually do, one line each. If the plan runs past a single page, it is doing too much -- cut it down or split it.
Be concrete
Vague steps stall; specific ones move.
| Too vague | Concrete |
|---|---|
| "Set up the project" | "Run npm create vite@latest" |
| "Add login" | "Install Lucia, add src/lib/auth.ts and the session middleware" |
| "Polish the UI" | "Apply spacing + dark-mode classes to Sidebar.tsx" |
The test: does the step have an outcome you could point at and verify?
Let the task type drive the content
New project: decide the stack first, define the smallest shippable slice, sketch the file layout.
Adding a feature: identify which files change, list new dependencies, decide how you will confirm it works.
Fixing a bug: pin down the root cause, name the exact file and line to change, state the test that proves it is fixed.
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.
- 1mo ago First seen · 108 lines · 87 tokens per session scan A b2abc687c2b6
plan-writing is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,054 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
web-platform-baseline
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale knowledge be stated as current. Triggers: user says "container query", "can I use", "browser support", "modern CSS", ":has"…
doc-coauthoring
Collaboratively author technical specifications, RFCs, PRDs, ADRs, and decision documents through structured context gathering, iterative refinement, and blind reader testing. Use when drafting substantial documentation, architecture proposals, or engineering design records.