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 yimwoo/hotl-plugin --skill writing-plansgit clone --depth 1 https://github.com/yimwoo/hotl-pluginWrote 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/yimwoo/hotl-plugin/writing-plans)<a href="https://agentmods.dev/skills/yimwoo/hotl-plugin/writing-plans"><img src="https://agentmods.dev/badge/skills/yimwoo/hotl-plugin/writing-plans.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.02900 |
| Opus 5 | $0.00015 | $0.01450 |
| Sonnet 5 | $0.00006 | $0.00580 |
| Haiku 4.5 | $0.00003 | $0.00290 |
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 8d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing HOTL Plans
Overview
Produce a dated workflow file that loop-execution can execute. The canonical filename is YYYY-MM-DD-<slug>-workflow.md, where <slug> is a short kebab-case identity derived from the intent (e.g., 2026-04-22-add-rate-limiting-workflow.md). Each step should be 2-5 minutes of work. Include loop conditions and gates from the design's governance contract.
When the accepted design defines execution limits, include only the relevant optional portable budget fields (max_total_attempts, max_agents, max_cost_usd, max_elapsed_minutes) in workflow frontmatter. Do not invent numeric budgets. policy_profile is descriptive and never grants host permissions.
Announce: "I'm using the writing-plans skill to create the executable workflow."
Output Filename
Save as YYYY-MM-DD-<slug>-workflow.md, where:
YYYY-MM-DDis the current local date<slug>is a short kebab-case semantic identity derived from the intent (e.g.,add-user-auth,refactor-api)
Examples:
2026-04-22-add-user-auth-workflow.md2026-04-22-refactor-api-workflow.md
The date makes workflow revisions easy to sort chronologically. The semantic identity remains <slug>, not the date-prefixed filename.
Semantic Identity
The canonical workflow filename is human-friendly, but the stable execution identity is still <slug>.
- Filename:
YYYY-MM-DD-<slug>-workflow.md - Semantic identity:
<slug> - Default branch derivation:
hotl/<slug>
When a later workflow revision is created for the same feature, it should use a new dated filename while keeping the same semantic identity.
Output Directory
Default: docs/plans. Opt-in override via .hotl/config.yml: workflows_dir: <path>. Resolution procedure:
- Resolve the install path of
hotl-config-resolve.shusing the same six-location rule documented fordocument-lint.shandhotl-config.sh(seeskills/document-review/SKILL.md):- In-repo:
scripts/hotl-config-resolve.sh - Codex native-skills install:
~/.codex/hotl/scripts/hotl-config-resolve.sh - Codex plugin install:
~/.codex/plugins/hotl-source/scripts/hotl-config-resolve.sh - Codex plugin cache fallback:
~/.codex/plugins/cache/codex-plugins/hotl/*/scripts/hotl-config-resolve.sh - Cline install fallback:
~/.cline/hotl/scripts/hotl-config-resolve.sh - Claude Code plugin fallback:
~/.claude/plugins/hotl/scripts/hotl-config-resolve.sh
- In-repo:
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.
- 8d ago First seen · 231 lines · 30 tokens per session scan A 269f7090f260
writing-plans is a skill published in the GitHub repository yimwoo/hotl-plugin (26 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 2,900 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
global_rules
Parent policy layer for approval-first coding workflows under both plain and imperial registers. Defines non-negotiable constraints, not the primary auto-trigger workflow.
approved-checklist-executor
Use only after a checklist or atomic slices have been explicitly approved. Execute approved slices under the current run mode, preserve atomic discipline, verify, archive one commit per slice, report git state, package evidence for review, and stop on blockers or replanning needs.
approval-first-planner
Use for implementation-style tasks that modify code, files, pages, or project structure. Inspect first, then output an approval-first execution contract with atomic slices, red lines, green tests, acceptance ladder, commit plan, target artifacts, and a white-box acceptance YAML bridge. Do not edit files.
free-development-mode
A workflow for carrying out coding work after the user explicitly activates free development mode. It allows pragmatic direct execution while keeping scope, safety boundaries, and engineering discipline explicit.
auditor-succession-prompt
A prompt package for creating a fresh auditor role under the Seven-Stars protocol. It defines the auditor’s identity, responsibilities, evidence boundaries, and limits, but does not perform the audit itself.
contract-hook-router
Route host-native plan/ask modes into Cyber-Ming contract lifecycle hooks. Use when a user asks to plan, execute, continue, take over, or when host plan mode should become an Atomic Execution Contract instead of free-form agent planning.