Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MereWhiplash/engram-cogitatornpx agentmods add skills/merewhiplash/engram-cogitator/writing-plansWrote 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/merewhiplash/engram-cogitator/writing-plans)<a href="https://agentmods.dev/skills/merewhiplash/engram-cogitator/writing-plans"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/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/merewhiplash/engram-cogitator/writing-plans"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/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 | $0.00023 | $0.00715 |
| Opus 5 | $0.00012 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Create implementation plans that an engineer with zero context can follow.
Announce: "I'm using the writing-plans skill to create the implementation plan."
Prerequisites
- Design document exists in
docs/designs/YYYY-MM-DD-<topic>.md - On a feature branch
Step 0: Load Context
Get project config and relevant patterns:
ec_search:
query: project config
type: config
ec_search:
query: [feature area] pattern
type: pattern
ec_search:
query: [feature area] implementation
type: learning
Note the configured test_command for TDD steps.
The Plan Structure
Plans go in docs/plans/YYYY-MM-DD-<topic>.md and cross-reference the design.
Header Template
# [Feature Name] Implementation Plan
**Design:** [docs/designs/YYYY-MM-DD-<topic>.md](../designs/YYYY-MM-DD-<topic>.md)
**Goal:** [One sentence]
**Architecture:** [2-3 sentences about approach]
**EC Context:** [List any relevant memories consulted]
---
Task Structure
Each task is bite-sized (2-5 minutes) and follows @tdd:
### Task N: [Component Name] @tdd
**Files:**
- Create: `exact/path/to/file.ts`
- Modify: `exact/path/to/existing.ts`
- Test: `tests/path/to/test.ts`
**Step 1: Write failing test** (RED)
\`\`\`typescript
test('specific behavior', () => {
// exact test code
});
\`\`\`
**Step 2: Run test, verify it fails**
\`\`\`bash
{test_command} path/to/test
\`\`\`
Expected: FAIL - "function not defined"
**Step 3: Implement minimal code** (GREEN)
\`\`\`typescript
// exact implementation code
\`\`\`
**Step 4: Run test, verify it passes** @verifying
\`\`\`bash
{test_command} path/to/test
\`\`\`
Expected: PASS
**Step 5: Commit**
\`\`\`bash
git add . && git commit -m "feat: add specific feature"
\`\`\`
Principles
- Exact file paths - No ambiguity
- Complete code - Not "add validation here"
- TDD every task - Test → Fail → Implement → Pass → Commit
- Frequent commits - One per task
- DRY/YAGNI - Don't over-engineer
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.
- 11d ago First seen · 131 lines · 23 tokens per session scan A 073b87b80c35
writing-plans is a skill published in the GitHub repository MereWhiplash/engram-cogitator (4 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 715 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.