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.
npx skills add clubpay/ronykit --skill writing-plansgit clone --depth 1 https://github.com/clubpay/ronykitWrote 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/clubpay/ronykit/writing-plans)<a href="https://agentmods.dev/skills/clubpay/ronykit/writing-plans"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/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/clubpay/ronykit/writing-plans"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00670 |
| Opus 5 | $0.00023 | $0.00335 |
| Sonnet 5 | $0.00009 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
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 9d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
For any multi-step change, write the plan before the code. A good plan lets someone with no context implement the work correctly, one small task at a time.
When to use
- You have a spec/requirements for a feature that touches multiple files or steps.
- Before starting non-trivial implementation (skip for one-line fixes).
Save plans to docs/plans/YYYY-MM-DD-<feature-name>.md (or the repo's
convention) so they're reviewable and durable.
1. Map the files first
Before listing tasks, decide which files are created or modified and the single responsibility of each. Decomposition decisions get locked in here.
- One clear responsibility per file; prefer small, focused files.
- Files that change together live together — split by responsibility, not layer.
- In an existing codebase, follow the established patterns; don't unilaterally restructure.
2. Right-size the tasks
A task is the smallest unit that carries its own test cycle and is worth a fresh reviewer's approval. Fold setup/config/scaffolding into the task whose deliverable needs them. Each task ends with an independently testable result.
3. Break tasks into bite-sized steps
Each step is one action (a couple of minutes), following a test-first loop:
- Write the failing test
- Run it; confirm it fails for the right reason
- Write the minimal code to pass
- Run it; confirm it passes
- Commit
Plan template
# <Feature> Implementation Plan
**Goal:** <one sentence — what this builds>
**Approach:** <2-3 sentences on the design>
**Tech / constraints:** <key libraries, version floors, project-wide rules>
## Task N: <component>
**Files:**
- Create: `exact/path/to/file`
- Modify: `exact/path/to/existing` (lines/area)
- Test: `exact/path/to/test`
**Interfaces:**
- Consumes: <signatures this task relies on from earlier tasks>
- Produces: <function names / types later tasks will use>
- [ ] Step 1 — write the failing test (`<run command>`, expect FAIL)
- [ ] Step 2 — minimal implementation
- [ ] Step 3 — run the test, expect PASS
- [ ] Step 4 — commit
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.
- 9d ago First seen · 87 lines · 46 tokens per session scan A e131473ca03e
writing-plans is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 46 tokens to every session and 670 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.
Other skills, from other repositories
ast-introspection
Use Go AST-aware analysis to enumerate symbols, extract signatures, and propose mechanically safe refactors (read-only by default).
build-run
Build and run the project locally to reproduce compile/runtime issues in a safe, non-production way.
ci-orchestrator
Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.
code-navigation
Rapid, focused navigation to locate definitions/usages and map the impact of proposed changes.
config-loader-helper
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
db-infra-mocks
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.