Borrowing it
Nothing to install: this file belongs to LEEI1337/phantom-neural-cortex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LEEI1337/phantom-neural-cortex/master/.claude/skills/writing-plans/SKILL.mdgit clone --depth 1 https://github.com/LEEI1337/phantom-neural-cortexWrote 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/leei1337/phantom-neural-cortex/writing-plans)<a href="https://agentmods.dev/skills/leei1337/phantom-neural-cortex/writing-plans"><img src="https://agentmods.dev/badge/skills/leei1337/phantom-neural-cortex/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.
<a href="https://agentmods.dev/skills/leei1337/phantom-neural-cortex/writing-plans"><img src="https://agentmods.dev/badge/skills/leei1337/phantom-neural-cortex/writing-plans.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 | $0.00016 | $0.00428 |
| Opus 5.5 | $0.00006 | $0.00171 |
| Sonnet 5.5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
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 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.
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.
What it actually says
Writing Implementation Plans
Create clear plans BEFORE coding to save time and tokens:
Plan Structure
1. GOAL (1-2 sentences)
What are we building and why?
2. CONSTRAINTS
- Technology limits
- Time/resource constraints
- Compatibility requirements
- Performance targets
3. APPROACH (High-Level)
- Architecture pattern
- Key components
- Data flow
- Integration points
4. STEPS (Ordered Tasks)
1. [Component] - Brief description
2. [Component] - Brief description
- Sub-task if needed
3. [Testing] - What to test
4. [Deployment] - How to deploy
5. RISKS & MITIGATIONS
Risk: Description
Mitigation: Solution
6. SUCCESS CRITERIA
- Measurable outcomes
- Test coverage targets
- Performance metrics
Token Optimization
- Write plan ONCE, reference during implementation
- Clear steps prevent back-and-forth
- Catches issues early (cheaper to fix in planning)
- Team can review before coding starts
Example Output Format
GOAL: Add user authentication with JWT
CONSTRAINTS:
- Must use existing DB schema
- Response time < 200ms
- Support OAuth2
APPROACH:
- Middleware-based auth layer
- JWT with refresh tokens
- Redis session cache
STEPS:
1. Create auth middleware
2. Implement token generation/validation
3. Add refresh token logic
4. Write integration tests
5. Update API docs
RISKS:
- Token expiry handling → Use refresh tokens
- Concurrency issues → Use Redis locks
SUCCESS:
- All endpoints secured
- 95%+ test coverage
- Load test passes (1000 req/s)
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 · 92 lines · 16 tokens per session scan A 4a1341f28bf3
writing-plans is a skill published in the GitHub repository LEEI1337/phantom-neural-cortex (5 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 428 once invoked, about $0.0001 per session on Opus 5.5. 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
brain-save
Save session context, decisions, progress, and plans to the Claude Brain Logseq graph. Triggers: "save to brain", "save this", "remember this", "store this decision", "log this", "save progress", "before I quit", "wrap up". Don't fire for read operations (use brain-load) or status checks (use brain-status).
brain-doctor
Lint and repair the Claude Brain Logseq graph — find and fix format violations that create phantom pages or broken macros. Triggers: "brain doctor", "lint brain", "check brain health", "clean up brain", "fix brain", "graph hygiene", "why are there empty pages", "find broken pages", "backfill digests", "rebuild digest…
brain-init
Set up the Claude Brain Logseq graph (first-time) or add a new project page. Triggers: "init brain", "setup brain", "init brain project ", "add project to brain". Don't fire for loads, saves, or status checks — those are handled by brain-load, brain-save, and brain-status.
brain-load
Load project context from the Claude Brain Logseq graph into the current session. Triggers: "load brain", "load ", "resume ", "continue work on ", "what do we know about ". Don't fire for write operations (use brain-save), generic questions about Logseq itself, or "open " / "switch to " requests that mean opening…
brain-status
Show a dashboard of all projects in the Claude Brain graph, or graph analytics. Dashboard triggers: "brain status", "show projects", "show brain", "what's in my brain", "project dashboard", "brain overview", "list projects", "summary". Analytics triggers: "brain stats", "graph analytics", "graph activity over time".…
release
Cut a logseq-brain release — eval gate, version bump in plugin.json and BRAINVERSION, tag, GitHub release, .plugin rebuild, skillsmith marketplace bump. Invoke only when the user asks to release.