writing-plans

writing-plans is a skill for Claude Code, Codex from GanyuanRan/Aegis. It costs 44 tokens per session (5,232 once invoked), scanned A, original, MIT.

A guide for writing a lasting implementation plan before starting a multi-step coding task. It covers requirements, affected files, small work steps, and checks for correctness.

In plain words
What is it for?
Use it when an approved specification requires coordinated changes across files, interfaces, data structures, or compatibility boundaries.
Why use it?
It gives a project a clear record of what will change and how the work will be verified before coding begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Part of the aegis plugin — 22 skills, 3 commands, 1 hook shipped together

Good fit Use it when an approved specification requires coordinated changes across files, interfaces, data structures, or compatibility boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ganyuanran/aegis/writing-plans
About the project

Aegis is a method pack that guides coding agents to inspect a project's baseline, make bounded changes, and verify their work with fresh evidence. It is for people using coding-agent hosts who want fewer unverified changes and less unnecessary process. The catalogue add-ons implement this method through skills, instructions, commands, a hook, and a plugin.

GanyuanRan/Aegis · 1,178 stars · on GitHub

Install

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.

Any agent
npx skills add GanyuanRan/Aegis --skill writing-plans
Clone the repo
git clone --depth 1 https://github.com/GanyuanRan/Aegis

Made for: Claude Code, Codex.

Or install aegis, the plugin that ships this one along with the rest of its 22 skills, 3 commands, 1 hook.

Wrote 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.

agentmods badge for writing-plans

README.md
[![agentmods](https://agentmods.dev/badge/skills/ganyuanran/aegis/writing-plans/github.svg)](https://agentmods.dev/skills/ganyuanran/aegis/writing-plans)
Your own site
<a href="https://agentmods.dev/skills/ganyuanran/aegis/writing-plans"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/writing-plans/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.

agentmods 80×15 button for writing-plans

Your own site · 80×15
<a href="https://agentmods.dev/skills/ganyuanran/aegis/writing-plans"><img src="https://agentmods.dev/badge/skills/ganyuanran/aegis/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 450
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.05232
Opus 5 $0.00022 $0.02616
Sonnet 5 $0.00009 $0.01046
Haiku 4.5 $0.00004 $0.00523

Measured 7d ago against content hash 91771c98e105, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

writing-plans 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 7d 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.

skills/writing-plans/SKILL.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute

→ Have an existing parent plan/spec and a tiny execution slice? → Use Planless Slice Lane.

  1. Emit a compact Slice Card: goal, parent plan/spec, files, boundary, verification, stop
  2. Update the parent workstream checkpoint/evidence/drift state if persistent state is needed
  3. Do not save a new plan for the micro-slice → Mechanical or bounded change with no durable boundary (no new owner, contract, schema, public API, migration, or compat surface)? → Use Planless Slice Lane without a parent document. Emit the compact Slice Card, skip the plan file, and record the change in the commit message. → Have approved spec/requirements for a new workstream or an escalation trigger? → Write implementation plan. Assume engineer has zero context.
  4. Scope check: fact/assumption/unknown, baseline, Requirement Ready Check, Ripple Signal Triage, compatibility boundary, dual-track needs
  5. File map: what files created/modified, clear boundaries, follow existing patterns
  6. Bite-sized tasks (2-5 min each): exact file paths, complete code, exact commands, expected output
  7. Self-review: spec coverage, placeholders, type consistency, compatibility, verification, dual-track
  8. Save → select and announce the execution route; proceed unless a real authorization or safety boundary requires the user → Plan must answer: problem, baseline, files, compat, verification, risks, retirement. → Escalate from Planless Slice Lane to a durable plan when the slice adds a new owner, contract, schema, public API, architecture boundary, migration, persistence, security/permission, distribution/release surface, or unclear verification boundary.

Read the full file on GitHub · 499 lines

Files

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.

Changes

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.

  1. 7d ago Changed · +9 lines 91771c98e105
  2. 11d ago First seen · 490 lines · 44 tokens per session scan A e0794871f909

Subscribe to this mod's changes

writing-plans is a skill published in the GitHub repository GanyuanRan/Aegis (1,178 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 5,232 once invoked, about $0.0002 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.

Related

Other skills, from other repositories