Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
A skill your agent uses when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being…
Install Writing Plans
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kid-sid/claude-spellbook writing-plans --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-plans .claude/skills/writing-plans && rm -rf skills-srcUse ~/.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/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .claude/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plansType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kid-sid/claude-spellbook writing-plans --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/writing-plans .agents/skills/writing-plans && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .agents/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kid-sid/claude-spellbook writing-plans --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/writing-plans .cursor/skills/writing-plans && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .cursor/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kid-sid/claude-spellbook.git --path skills/writing-plans--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kid-sid/claude-spellbook writing-plans --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/writing-plans .gemini/skills/writing-plans && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .gemini/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kid-sid/claude-spellbook writing-plansInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/writing-plans .github/skills/writing-plans && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .github/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kid-sid/claude-spellbook --skill writing-plans -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kid-sid/claude-spellbook writing-plans --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/writing-plans .opencode/skills/writing-plans && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "writing-plans" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/writing-plans into .opencode/skills/writing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-plans", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
writing-plans- GitHub stars
- 190
- Token cost
- ~1.5k tokens
- SKILL.md length
- 575 words
- Files
- 1
- Skills in repo
- 55
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being…
- Creating an implementation plan for a non-trivial task — any change spanning multiple files
- SKILL.md covers When to Activate, The Zero-Placeholder Rule, Plan Structure and Sequencing Rules, plus 4 more sections
- Calls pytest; needs STRIPE_SECRET_KEY
- Involving a database migration
What it does
Writing Plans is an agent skill from kid-sid/claude-spellbook. Use when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being handed off to a subagent for execution.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Planning, Database migrations and Subagents. The repository describes itself as: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.
When your agent uses it
- Creating an implementation plan for a non-trivial task — any change spanning multiple files
- Involving a database migration
- Requiring specific sequencing
- Being handed off to a subagent for execution
Example prompts
- “/writing-plans”
Requirements
- A credential in STRIPE_SECRET_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit a7c2ac9. 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
Shell commands in SKILL.md call:
pytest
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 these keys or tokens, usually read from environment variables:
STRIPE_SECRET_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Writing Plans loads about 1.5k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 575 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:32
y" | `STRIPE_SECRET_KEY=sk_test_...` in `.env` |
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 kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 575 words, ~1,487 tokens.
Download SKILL.mdSave it as
.claude/skills/writing-plans/SKILL.md (or your agent's skills folder).- name
- writing-plans
- description
- Use when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being handed off to a subagent for execution.
Writing Plans
A plan is only useful if it's specific enough that a stranger could execute it without asking questions.
When to Activate
- Creating a plan for a feature that touches more than 2 files
- Planning a refactor where the sequence of steps matters
- Designing a database migration or schema change
- Writing a plan to hand off to a subagent for implementation
- Any task where "implement X" is too vague to be actionable
- Planning work that requires specific test commands or rollback steps
- Onboarding a contributor to an ongoing task mid-stream
The Zero-Placeholder Rule
Every element of a plan must be fully specified. If you write it, it must be complete — no fill-in-the-blank, no ellipsis, no "implement as needed."
| Element | BAD — placeholder | GOOD — complete |
|---|---|---|
| File path | path/to/file.py | src/api/routes/users.py |
| Code change | "add validation logic" | Full code block with the exact function |
| Test command | "run the tests" | pytest tests/api/test_users.py::test_create_user -v |
| Expected output | "tests pass" | PASSED tests/api/test_users.py::test_create_user |
| Commit message | "fix the bug" | fix(auth): reject tokens with expired nbf claim |
| Config value | "appropriate timeout" | timeout: 30s |
| Environment variable | "set the API key" | STRIPE_SECRET_KEY=sk_test_... in .env |
Plan Structure
## Goal
One sentence: what this plan achieves and why.
## Pre-conditions
- [ ] Specific thing that must be true before starting: `command` → expected output
- [ ] Environment variable or service that must be running
## Steps
### Step 1 — <verb> <specific target>
**File:** `absolute/path/to/file.ext`
\`\`\`language
// Full code block — no ellipsis, no "rest of function", no TODO comments
\`\`\`
**Verify:** `exact command` → `expected output`
### Step 2 — commit checkpoint
**Commit:** `type(scope): specific description of what changed`
## Rollback
- If step 3 fails: `exact command to undo`
- If migration was applied: `alembic downgrade -1`Sequencing Rules
| Rule | Reason |
|---|---|
| One concern per step | Bundled steps are harder to roll back and harder to verify |
| Database migrations before code changes | Code errors if it references a column that doesn't exist yet |
| Write the failing test before implementation | Confirms the test actually tests what you think |
| Include a commit at natural checkpoints | Enables bisect and partial rollback |
| Pre-conditions listed before any step | Eliminates "I didn't know I needed X" failures mid-plan |
Forbidden Patterns
# BAD — relative path
Update the config in `settings.py`
# GOOD — absolute path
Update `src/config/settings.py` (absolute from repo root)# BAD — vague instruction
Add error handling to the endpoint
# GOOD — complete instruction
In `src/api/routes/users.py` line 47, wrap the db.query() call:
try:
result = db.query(User).filter(User.id == user_id).first()
except SQLAlchemyError as e:
logger.error("db_query_failed", user_id=user_id, error=str(e))
raise HTTPException(status_code=500, detail="Internal server error")# BAD — no expected output
Run the tests to verify everything works.
# GOOD — exact command + expected output
$ pytest tests/api/test_users.py -v
PASSED tests/api/test_users.py::test_get_user_returns_404_when_not_found
PASSED tests/api/test_users.py::test_get_user_returns_user_data
2 passed in 0.43sWhen to Plan vs. When to Code
| Situation | Approach |
|---|---|
| Single-file change, < 30 lines | Code directly; inline context in chat |
| Multi-file change, clear sequence | Write a full plan first |
| Subagent will implement | Always a written plan — agents can't ask clarifying questions |
| Database migration involved | Always a written plan — irreversible if done wrong |
| Rollback must be possible | Always a written plan |
| Shape of solution is unknown | Brainstorm first; plan after the approach is clear |
| Pairing or handoff to a teammate | Written plan with pre-conditions and verify steps |
Show full SKILL.md (231 more words)Show less
Red Flags
- "Implement X" as a plan step — this is a task description, not a plan; expand into specific files, code, and verify commands
- Relative file paths — ambiguous across machines and working directories; always specify paths from a known root
- No verify step after a destructive operation — you won't know it succeeded until something later fails unexpectedly
- Bundled steps ("do A and B and C together") — if B fails, you can't tell what state A left the system in
- Missing rollback for irreversible steps — database migrations, published events, external API calls all need explicit undo instructions
- "Add tests" without specifying which file, which test case, and what the assertion checks
- Missing pre-conditions — forgetting to list required services, env vars, or setup that must exist before step 1
- Commit messages written as "update files" — write the actual message; vague messages make bisect and blame useless later
Checklist
- Every file path is specified from a known root (no bare filenames)
- Every code change is a complete, runnable code block (no ellipsis or TODO)
- Every destructive step has a verify command with expected output
- No step says "implement", "add", or "update" without full specifics
- Database migrations precede model/code changes
- Commit messages are written out verbatim
- Rollback instructions exist for irreversible steps
- Pre-conditions are listed and checkable before step 1
- A person who has never seen this codebase could execute the plan without asking questions
© kid-sid, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/writing-plans of kid-sid/claude-spellbook.
Open the folder on GitHubat commit a7c2ac9
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Writing Plans this skillkid-sid/claude-spellbook | 190 | — | ~1.5k | Automated safety check: Notes | MIT | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Executing PlansGanyuanRan/Aegis | 1.3k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Execumputun/cc-thingz | 484 | — | ~8k | Automated safety check: Pass | MIT | |
| Autopilot End-to-End Buildernick-vels/skills | 411 | — | ~2.5k | Automated safety check: Notes | MIT | |
| Workflow Orchestrationvxcozy/workflow-orchestration | 116 | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Executing Plans
GanyuanRan/Aegis
A skill your agent uses when executing a written implementation plan across sessions or with review checkpoints.
Exec
umputun/cc-thingz
Execute plan tasks sequentially using subagents. An agent skill from umputun/cc-thingz.
Autopilot End-to-End Builder
nick-vels/skills
Builds an app, site, bot or feature from a spoken idea through requirements, spec, tickets, subagent work, review and acceptance, with a live progress dashboard.
Workflow Orchestration
vxcozy/workflow-orchestration
Disciplined task execution with planning, verification, and self-improvement loops.
Blueprint
byungjunjang/jangpm-meta-skills
Agentic system design blueprint generator. An agent skill from byungjunjang/jangpm-meta-skills.
More from kid-sid/claude-spellbook
All 55 skills in this repoAccessibility
kid-sid/claude-spellbook
A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…
Agentex
kid-sid/claude-spellbook
A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…
AI Engineer
kid-sid/claude-spellbook
A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…
Angular
kid-sid/claude-spellbook
A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…
API Design
kid-sid/claude-spellbook
A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…
Auth
kid-sid/claude-spellbook
A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…
Related
Categories
Questions about Writing Plans
What does Writing Plans do?
A skill your agent uses when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being…. Writing Plans is an agent skill from kid-sid/claude-spellbook. Use when creating an implementation plan for a non-trivial task — any change spanning multiple files, involving a database migration, requiring specific sequencing, or being handed off to a subagent for execution.
When should I use Writing Plans?
Writing Plans fits situations like: creating an implementation plan for a non-trivial task — any change spanning multiple files; involving a database migration; requiring specific sequencing; being handed off to a subagent for execution.
How do I install Writing Plans in Claude Code?
Run `npx skills add kid-sid/claude-spellbook --skill writing-plans -a claude-code`. Or copy the skill folder (skills/writing-plans in kid-sid/claude-spellbook) 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 kid-sid/claude-spellbook --skill writing-plans -a codex`. Or copy the skill folder (skills/writing-plans in kid-sid/claude-spellbook) 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 kid-sid/claude-spellbook --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?
Going by SKILL.md and its folder, Writing Plans needs the command-line tools its instructions call (pytest) and credentials named STRIPE_SECRET_KEY. Our summary lists: A credential in STRIPE_SECRET_KEY.
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 notes only (mentions a .env file), nothing it rates as a warning. 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 1.5k tokens (SKILL.md is roughly 5.9k 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: Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Executing Plans (GanyuanRan/Aegis, 1.3k stars), Exec (umputun/cc-thingz, 484 stars) and Autopilot End-to-End Builder (nick-vels/skills, 411 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Writing Plans?
kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 190 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on August 5, 2026.
Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.