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 bengous/claude-code-plugins --skill thorough-plangit clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/thorough-plan)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/thorough-plan"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/thorough-plan/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/bengous/claude-code-plugins/thorough-plan"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/thorough-plan.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 | $0.00094 | $0.01461 |
| Opus 5 | $0.00047 | $0.00731 |
| Sonnet 5 | $0.00019 | $0.00292 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
thorough-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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thorough Plan
An adaptive exploration loop that prevents premature planning. Builds context through codebase exploration, targeted research, and user questions — then hands off to the normal planning flow.
This is not a planning framework. It's a context amplifier.
This skill injects judgment: explore what you can, ask what you must, stop when you know enough.
Triage
Read the brief. Evaluate along these dimensions:
- Ambiguity — multiple valid interpretations? unclear boundaries?
- Scope — how many files/systems? cross-cutting concerns?
- Risk — breaking changes? security? data migration?
- Novelty — unfamiliar library? new pattern for this codebase?
Low on all → skip exploration. State your understanding of the task and proceed directly to planning. Don't explore for the sake of exploring.
High on any → enter the exploration loop. Focus exploration on the dimensions that are actually uncertain.
- Ambiguity: low — intent is clear
- Scope: medium — needs new command + script, touches plugin structure
- Risk: low — read-only git operations, no data loss
- Novelty: low — similar commands exist in git/
→ One focused Explore agent on git/ patterns, then proceed to planning. No user questions needed.
- Ambiguity: high — "redesign" could mean anything from a new config format to a complete architecture change
- Scope: high — touches every plugin
- Risk: high — breaking change for existing plugins
- Novelty: medium — depends on what approach is chosen
→ Explore current config patterns across plugins, then ask the user what "redesign" means to them before exploring further.
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.
- yesterday Changed 60ef10f169f1
- 9d ago First seen · 163 lines · 94 tokens per session scan A a0f467e18766
thorough-plan is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,461 once invoked, about $0.0005 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
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
merge
Merge the reviewed pull request for the current branch, then hand straight off to cleanup. A sentence of editorial direction alongside the green light is read as a rider. Use when a human green-lights an open PR.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.