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 agentmods add skills/soulcodex/agentic/write-plannpx skills add soulcodex/agentic --skill write-plangit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00084 | $0.00977 |
| Opus 5 | $0.00042 | $0.00489 |
| Sonnet 5 | $0.00017 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
write-plan 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Plan Skill
Automatically capture every agent-produced plan as a discoverable file in
.agentic/plans/ — so plans are preserved locally but never pollute the git tree.
When a plan is tied to a GitHub issue and issue persistence is desired, prefer
github-issue-planning for issue-backed plan persistence on GitHub (prefer MCP,
fallback to gh CLI). Keep this skill as the local-file persistence path.
This skill is agent-invoked, not user-invoked. Do not prompt the user for metadata. Derive everything from context and write silently.
Step 1 — Derive Metadata from Context
Extract automatically — no prompts:
- Title: from the plan's main heading or the task description.
- Type: infer from the nature of the work:
feature— new capability being addedarchitecture— structural or design decisiondecision— a choice between alternativesrefactor— improving existing code without behaviour changeinvestigation— exploring a problem or unknown
- Status: always
drafton auto-save. - Affected: list of modules, files, or systems touched by the plan.
- Author: the agent name or model identifier.
Step 2 — Build the Filename
YYYY-MM-DD-{kebab-case-title}.md
Rules:
- Use today's date in
YYYY-MM-DDformat. - Slugify the title: lowercase, replace spaces and special characters with
-, strip leading/trailing hyphens. - If a file with the same slug already exists for today, append
-2,-3, etc.
Examples:
2026-04-04-add-golang-manual-di-skill.md
2026-04-04-refactor-auth-module.md
Step 3 — Write the Plan File
Save to .agentic/plans/{filename} using plan-template.md as the structure.
Mandatory sections (never omit):
- Context — what situation or problem prompted this plan?
- Goals — verifiable bullet points (done / not done).
- Approach — key decisions, alternatives considered, rationale.
- Steps — ordered list of concrete tasks.
- Risks & Open Questions — unknowns and blockers.
- Outcome — leave blank; filled in when status moves to
completed.
What ships with it
1 file 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.
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.
- 2d ago First seen · 139 lines · 84 tokens per session scan A de78571d7acc
write-plan is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 977 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 2026-08-31.
Other skills, from other repositories
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
design-system-governance
Define how the system evolves — contribution model, versioning, deprecation, and change management. Use when multiple teams contribute. For driving uptake use design-system-adoption (designer-toolkit); for design file history use version-control-strategy (design-ops).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).