Agent skill

Writing Plans

by GanyuanRan in GanyuanRan/Aegis

A skill your agent uses when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code.

MITAuto-check passedAgent Workflows

Install Writing Plans

skills CLI
$ npx skills add GanyuanRan/Aegis --skill writing-plans -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GanyuanRan/Aegis writing-plans --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GanyuanRan/Aegis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-plans .claude/skills/writing-plans && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
writing-plans
GitHub stars
1.3k
Used in
1 other repo
Token cost
~3.3k tokens
SKILL.md length
1,673 words
Files
3
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code.

  • You have an approved spec
  • SKILL.md covers TDD Route Guard, Entry And Artifact Choice, Aegis Project Workspace and Default Plan Surface, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Written requirements for a multi-step task that needs a durable plan document before touching code

What it does

Writing Plans is an agent skill from GanyuanRan/Aegis. Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `expanded-planning-guidance.md` and `plan-document-reviewer-prompt.md`).

It sits in Agent Workflows, covering Planning. The repository describes itself as: Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks. The licence is MIT.

When your agent uses it

  • You have an approved spec
  • Written requirements for a multi-step task that needs a durable plan document before touching code

Example prompts

  • “/writing-plans”

What it can do on your machine

Read from SKILL.md and the folder at commit 61867e9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Plans loads about 3.3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 1,673 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GanyuanRan/Aegis at commit 61867e9, republished under its MIT licence (© GanyuanRan). 1,673 words, ~3,284 tokens.

Download SKILL.mdSave it as .claude/skills/writing-plans/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
writing-plans
description
Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.
<EXPLICIT-MODE-GATE>
If activation mode is explicit (`~/.config/aegis/config.toml` has
`activation_mode = "explicit"`, or `AEGIS_ACTIVATION_MODE=explicit` is visible
in the environment) and the current user request did not explicitly invoke
Aegis or this skill by name, exit back to the fast path: answer concisely
without this workflow's checklist, ceremony, or document requirements. If the
user explicitly named Aegis or this skill, proceed normally.
</EXPLICIT-MODE-GATE>

Execute

→ Existing parent plan/spec and a tiny execution slice? → Use Planless Slice Lane. → 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. → Approved spec/requirements for a new workstream or an escalation trigger? → Write an implementation plan for an engineer with no prior task context.

For a durable plan: confirm scope and acceptance, map current owners/files, record the TDD route, decompose into executable tasks, define verification and retirement, self-review, save, then select the execution route. Proceed unless a real authorization or safety boundary requires the user.

Escalate from Planless Slice Lane when the work adds a new owner, contract, schema, public API, architecture boundary, migration, persistence, security/permission, distribution/release surface, or an unclear verification boundary.

Writing Plans

This skill turns approved requirements into a bounded, executable plan. The plan must answer: what changes, why code is necessary, which existing owner and files change, what stays compatible, what verifies the result, what risk remains, and what old path is retired or deliberately retained. A plan is method-pack guidance; it cannot grant authoritative completion.

TDD Route Guard

Before task decomposition, record TDD Route with mode (off | auto), decision (strict | light | skipped), authority, test posture, reason, and verification.

Strict RED / GREEN steps belong only to an explicit user/project TDD request or TDD Route: strict. In off, use skipped unless explicit strict authority overrides it. An approved plan or a risk label alone is not strict authority.

In auto, select strict for behavior, bugfix, shared/core, contract, persistence, permission, migration, producer/consumer, or meaningful regression signals. Select light only when the work is tiny, low-risk, single-owner, has no behavior change or strict signal, and has an obvious focused check. Absence of an explicit user TDD request is never evidence for light; the auto decision itself must be recorded.

If risk remains unknown, return to requirements, debugging, or plan review before task decomposition; do not infer a TDD route from uncertainty.

Only a strict decision with stated authority may prescribe failing-test, RED, GREEN, and REFACTOR steps. Otherwise plan the minimum change plus diagnostic reproduction or post-change regression. A missing auto decision returns to route selection before implementation tasks.

Entry And Artifact Choice

Announce at start: on the plan-writing route, say that this skill is creating the implementation plan. On Planless Slice Lane, announce the lane instead and do not claim a plan is being created.

Execution context: Reuse the current branch/workspace by default. A branch needs independent history; a worktree needs concurrent checkout, blocking unrelated dirty state, or explicit user/repository authority.

Input: approved requirements, a Spec Brief, or a Design Spec.

Default plan path: docs/aegis/plans/YYYY-MM-DD-<feature-name>.md. Plans do not go in work/; user and repository authority override the default.

Exception: use Planless Slice Lane when an existing parent plan/spec already owns the current tiny execution slice, or when the change is mechanical or bounded and needs no parent document. Do not save a new plan. Emit a compact Slice Card:

text
Slice Card:
- Goal:
- Parent plan/spec:
- Files:
- Boundary:
- Verification:
- Stop:

On the no-parent branch, Parent plan/spec: is none — direct bounded request.

Aegis Project Workspace

Workspace creation is lazy and follows project authority. The Aegis Method Pack repository must not create or ship a live docs/aegis/ workspace. When a durable plan must initialize or update another project's workspace, read the workspace section of expanded-planning-guidance.md. It owns the <aegis-workspace-helper> and INDEX.md command detail, not the decision to create a plan.

Default Plan Surface

Compact output contract: express these as natural plan content, not a stack of cards: Aegis Visibility, approved scope and plan basis, required baseline refs, files/owners, compatibility boundary, Change Necessity, TDD route, tasks, verification, risks, and retirement. Keep conditional structures silent unless their trigger below fires.

Aegis Visibility is normally one sentence explaining which owner, contract, retirement, compatibility, or verification pressure makes a durable plan useful. Structured trace belongs only to audit, debug, release, long-task review, or explicit request.

Before tasks, perform a Requirement Ready Check: identify the approved source, scope, scenarios, and acceptance evidence. If any decision-changing item is missing, do not create implementation tasks; return the smallest gap to the requirement/spec owner.

Perform Change Necessity before any non-trivial source edit or any new source-code path. This is behavior-triggered, not prompt-triggered. State naturally why no-change/docs/config is insufficient and name the minimum code boundary. A tiny helper, guard, branch, fallback, adapter, or owner is not exempt. A no-change, docs/config-only, or needs-clarification result narrows or stops the code plan.

Run Ripple Signal Triage before tasks when the change touches shared/core or cross-module behavior; a public API, schema, contract, compatibility, persistence, cache, export/readback, fallback, adapter, duplicate/legacy owner, retirement path, or both producer and consumer. If no signal fires, add no output. If one fires, identify the canonical owner and affected downstream consumers, state source-of-truth/contract/fallback/retirement risk, and carry expanded verification into the relevant task. A required owner/public-contract/source-of-truth change, retaining two owners, or adding a fallback, adapter, or compatibility branch returns to design or requires explicit prior alignment before implementation.

Run a compact Plan Pressure Test before task decomposition: test owner / contract / retirement fit, higher-level architecture path, verification scope, and task executability. It may proceed, revise the plan, or return to design; it is not an approval authority.

Show full SKILL.md (751 more words)Show less

Conditional Detailed Guidance

For interface/interaction work, compose ui-ux-governance and carry the accepted experience criteria and corresponding checks into affected tasks. Include API changes that alter visible states or recovery; keep backend-only work scoped.

Read only the trigger-matched section of expanded-planning-guidance.md:

  • ## Baseline And Requirement Detail when specific baseline acknowledgement needs structure or requirement readiness is incomplete/disputed;
  • ## New-Surface And Architecture Detail when a new surface or new owner needs Existence Check, AEGIS_MINIMALITY_REFERENCE, Architecture Integrity Lens, or first-principles-review detail before task decomposition;
  • ## Complexity Detail when material file-size, mixed-owner, add-in-place, adapter, fallback, or shared-core pressure appears;
  • ## Execution Readiness Detail for a long-running, handoff-prone, subagent-driven, high-risk architecture/contract/compatibility/retirement handoff;
  • ## Workspace Save Detail only when saving requires workspace initialization or INDEX.md updates;
  • ## Execution Route Detail only when route evidence needs a structured handoff; and
  • ## Expanded Plan Review only for an independent high-risk or handoff-heavy review.

The direct triggers cover baseline readiness, new surface or new owner, complexity pressure, workspace persistence, and execution handoff. The reference supplies detail only. This main file owns routing, plan versus Planless selection, task blocking, and execution handoff.

For a new surface, use Existence Check and docs/current/AEGIS_MINIMALITY_REFERENCE.md before tasks. Reuse an existing owner when it is sufficient. If owner, contract, responsibility overlap, higher-level simplification, fallback, or retirement remains risky, use the Architecture Integrity Lens and first-principles-review before task decomposition.

For maintained source, screen file shape, owner fit, add-in-place risk, and a better boundary. With no pressure signal, a compact edit-in-place decision is enough. When pressure exists, load the expanded Plan-Time Complexity Check and Complexity Budget. An over-budget result must change the task boundary, add governance work, or stop for follow-up.

For an ordinary medium/high handoff, state Intent Lock, Scope Fence, Baseline Lock, tests, and drift stop naturally. Load the expanded Execution Readiness View only for the auditable handoff triggers above. Neither form is a GateDecision, PolicySnapshot, approval gate, or completion authority.

If the plan must choose among deleting an old internal path, retaining a proven external compatibility boundary, or stopping for persistent-state confirmation, compose anti-entropy-governance. It does not authorize destructive execution.

Preserve approved ADR signal preservation, source refs, alternatives, compatibility, and baseline-sync questions for completion; do not create accepted architecture memory from an unexecuted plan.

Planless Slice Lane

Use Planless Slice Lane before writing or saving a plan when one of these entry conditions holds:

  • a parent spec or parent plan already defines the workstream, and the current request is executing or refining one bounded task from that parent
  • the change is mechanical or bounded and needs no parent document (the no-parent branch under # Execute)

and both of these are true:

  • no new owner, contract, schema, public API, architecture boundary, migration, persistence, security/permission, distribution/release surface, or unclear verification boundary appears
  • the slice can be described by a Slice Card

The lane preserves long-task continuity without turning execution bookkeeping into durable planning artifacts. A parent scope or acceptance mismatch returns to the parent plan/spec instead of spawning a micro-plan.

Plan And Task Quality

Map files before tasks. Follow existing ownership and naming. For non-trivial plans, passively use relevant current terms from CONTEXT-MAP.md or CONTEXT.md; route a real semantic conflict to establishing-project-context.

Every durable plan starts with Goal, Architecture, Tech Stack, Baseline/Authority Refs, Compatibility Boundary, TDD Route, and Verification. Then define small, ordered tasks with exact files, purpose, minimum necessary change, compatibility impact, and commands/outcomes that prove the task. Include code excerpts only when a signature, contract, or transformation would otherwise remain ambiguous; do not duplicate the implementation inside the plan.

For bug fixes, refactors, contract changes, or governance cleanup, keep Repair Track and Retirement Track explicit in the affected task. A retained old owner or fallback needs a reason and retirement trigger.

Self-review once for approved-scope coverage, placeholders, owner/type consistency, minimum change boundary, compatibility, exact verification, conditional trigger handling, and retirement. Fix defects inline. Tasks are execution units, not Git history units: the coordinator captures TaskStartSnapshot and creates one scoped commit only after the whole Task is reviewed and freshly verified.

Execution Handoff

The agent owns the execution-route decision. Select subagent-driven only for genuinely independent tasks with bounded ownership when coordination pays for it; otherwise select inline. Unavailable subagents falls back to inline execution. A dirty workspace alone does not select either route.

Ask the user only for unresolved authorization, privacy, paid-resource, external-action, irreversible-action, scope, acceptance, or workspace-ownership boundaries. Otherwise proceed immediately. State the decision, evidence, fallback, and User confirmation required: no | yes — <boundary> compactly; load the reference only when the full Execution Route schema is useful.

For subagent-driven, use aegis:subagent-driven-development. For inline, use aegis:executing-plans.

© GanyuanRan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/writing-plans of GanyuanRan/Aegis.

  • SKILL.md
  • expanded-planning-guidance.md
  • plan-document-reviewer-prompt.md

Open the folder on GitHubat commit 61867e9

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in GanyuanRan/Aegis, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Writing Plans next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Plans compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Plans this skillGanyuanRan/Aegis1.3k1 repos~3.3kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Interview Meaddyosmani/agent-skills105k6 repos~3.8kAutomated safety check: PassMIT
OpenSpec Guided OnboardingFission-AI/OpenSpec72k1 repos~4.5kAutomated safety check: PassMIT
Writing Plansgeeksblabla/stateofdev.ma16358 repos~661Automated safety check: PassNone
Subagent Driven DevelopmentAsvarox/allkaraoke26138 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    105k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • OpenSpec Guided Onboarding

    Fission-AI/OpenSpec

    Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.

    72k GitHub starsUsed in 1 repo~4.5k tokens
    Agent WorkflowsAuto-check passed
  • Writing Plans

    geeksblabla/stateofdev.ma

    A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…

    163 GitHub starsUsed in 58 repos~661 tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 38 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Planning With Files

    jd-opensource/JoySafeter

    Implements Manus-style file-based planning for complex tasks.

    314 GitHub starsUsed in 19 repos~1.8k tokens
    Agent WorkflowsAuto-check: notes

More from GanyuanRan/Aegis

All 21 skills in this repo
  • Anti Entropy Governance

    GanyuanRan/Aegis

    A skill your agent uses when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically…

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • Executing Plans

    GanyuanRan/Aegis

    A skill your agent uses when executing a written implementation plan across sessions or with review checkpoints.

    1.3k GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed
  • First Principles Review

    GanyuanRan/Aegis

    A skill your agent uses when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture…

    1.3k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Goal Framing

    GanyuanRan/Aegis

    A skill your agent uses when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

    1.3k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • A skill your agent uses when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling.

    1.3k GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check: warnings
  • A skill your agent uses when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync…

    1.3k GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

Categories

Questions about Writing Plans

What does Writing Plans do?

A skill your agent uses when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Writing Plans is an agent skill from GanyuanRan/Aegis. Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code.

When should I use Writing Plans?

Writing Plans fits situations like: you have an approved spec; written requirements for a multi-step task that needs a durable plan document before touching code.

How do I install Writing Plans in Claude Code?

Run `npx skills add GanyuanRan/Aegis --skill writing-plans -a claude-code`. Or copy the skill folder (skills/writing-plans in GanyuanRan/Aegis) into .claude/skills/writing-plans in your project. Claude Code loads it when a task matches its description.

How do I install Writing Plans in Codex?

Run `npx skills add GanyuanRan/Aegis --skill writing-plans -a codex`. Or copy the skill folder (skills/writing-plans in GanyuanRan/Aegis) into .agents/skills/writing-plans in your project. Codex loads it when a task matches its description.

Can I use Writing Plans in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GanyuanRan/Aegis --skill writing-plans -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-plans, .gemini/skills/writing-plans, .github/skills/writing-plans and .opencode/skills/writing-plans in your project.

What does Writing Plans need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Plans is instructions for the agent only.

Does Writing Plans access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Writing Plans safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Plans use?

Writing Plans is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Plans use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Plans?

Skills that share tags, products or a category with Writing Plans: Executing Plans Inline (obra/superpowers, 297k stars), Interview Me (addyosmani/agent-skills, 105k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 72k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Plans?

GanyuanRan (a GitHub user) maintains it in GanyuanRan/Aegis, which has 1,337 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 10, 2026.

Source: GanyuanRan/Aegis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.