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 johnqtcg/awesome-skills --skill writing-plansgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/writing-plans)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/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/johnqtcg/awesome-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/writing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 91 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 188 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00071 | $0.03174 |
| Opus 5 | $0.00036 | $0.01587 |
| Sonnet 5 | $0.00014 | $0.00635 |
| Haiku 4.5 | $0.00007 | $0.00317 |
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
Write implementation plans that a developer with zero codebase context can follow. Plans must be evidence-backed (paths verified), mode-appropriate (not over-engineered), and executable (every step has a verification command). Before planning, verify that the user's requirements are clear enough to plan against.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Gate 1: Requirements Clarity Gate
Before classifying complexity, verify the request is plannable. A vague request produces a plan built on assumptions.
Fast pass-through: If the request names specific files, describes concrete behavior changes, and has clear scope boundaries, proceed directly to Gate 2. Do not ask clarifying questions for obviously clear requests.
STOP and ASK if any of these apply:
| Trigger | What's Missing | Example |
|---|---|---|
| Vague action verb with no measurable outcome | Success criteria | "optimize the auth module" |
| No scope boundary stated | What's in/out of scope | "refactor the codebase" |
| Ambiguous target when multiple exist | Which component | "update the API" (when 5 APIs exist) |
| Change type unclear (behavior vs performance vs structure) | Intent | "improve error handling" |
| Backward compatibility unstated for public interface changes | Constraint | "change the response format" |
Clarification protocol:
- State what you understood (to confirm or correct)
- Ask only about WHAT the user wants, not HOW to implement it
- Group related questions — max 3-5 questions per round
- Maximum 2 clarification rounds. If still unclear after round 2, state remaining assumptions explicitly and proceed
- For each assumption you make, mark it as
[Assumption]in the plan header
Exit condition: Requirements are "clear enough" when you can write a one-sentence Goal and a scope boundary (what changes, what does NOT change) without inventing information the user did not provide.
Load references/requirements-clarity-gate.md for the full dimension checklist, mode-appropriate depth rules, and clarification examples.
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- plan-document-reviewer-prompt.md 3.7 KB
- references/anti-examples.md 3.7 KB
- references/applicability-gate.md 2.3 KB
- references/golden-scenarios.md 5.1 KB
- references/plan-templates/api-change.md 1.5 KB
- references/plan-templates/bugfix.md 1.3 KB
- references/plan-templates/docs-only.md 1.4 KB
- references/plan-templates/feature.md 1.3 KB
- references/plan-templates/migration.md 1.7 KB
- references/plan-templates/refactor.md 1.6 KB
- references/plan-update-protocol.md 1.7 KB
- references/repo-discovery-protocol.md 2.3 KB
- references/requirements-clarity-gate.md 6.3 KB
- references/reviewer-checklist.md 4.7 KB
- scripts/run_regression.sh 436 B runs code
- scripts/tests/golden/api-breaking-change-good.json 2.4 KB
- scripts/tests/golden/bugfix-plan-good.json 730 B
- scripts/tests/golden/degraded-mode-plan.json 1.1 KB
- scripts/tests/golden/docs-only-skip.json 517 B
- scripts/tests/golden/feature-plan-bad.json 1.2 KB
- scripts/tests/golden/feature-plan-good.json 2.3 KB
- scripts/tests/golden/migration-plan-good.json 3.7 KB
- scripts/tests/golden/monorepo-deep-plan-good.json 3.6 KB
- scripts/tests/golden/partial-discovery-inferred.json 1.9 KB
- scripts/tests/test_golden_scenarios.py 7.3 KB runs code
- scripts/tests/test_skill_contract.py 26 KB runs code
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 · 303 lines · 71 tokens per session scan A b5227175d35a
writing-plans is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 3,174 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.