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 richkuo/rk-skills --skill fableplangit clone --depth 1 https://github.com/richkuo/rk-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/richkuo/rk-skills/fableplan)<a href="https://agentmods.dev/skills/richkuo/rk-skills/fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fableplan/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/richkuo/rk-skills/fableplan"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fableplan.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 | $0.00109 | $0.01613 |
| Opus 5 | $0.00055 | $0.00807 |
| Sonnet 5 | $0.00022 | $0.00323 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
fableplan 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fableplan
A Fable 5.1 Plan subagent writes the plan. The main agent checks it, posts it, and builds from it. The subagent never builds.
Input
A task description, with an optional issue reference (URL, #<N>, bare <N>, or owner/repo#N). With an issue, the plan is also posted as a comment. Ask what to plan only when the task is unclear. With no issue, never invent one or post anywhere.
Steps
1. Resolve the GitHub issue (only if one is referenced)
gh issue view <N> --json number,title,body,url (add -R owner/repo for another repository). Stop and tell the user if it fails; never plan from a paraphrase of an issue you could not fetch. Record the number and URL for step 4. Read any Plan effort line in the body's ## Execution block: planning runs at that tier when present, else high; a stamped xhigh runs at xhigh.
2. Dispatch the Fable 5.1 Plan subagent
Do not plan the task yourself first. Load the fable-dispatch skill before dispatching. It owns the ladder, the CLI shim (--effort <tier> carries the tier there), result parsing, attribution (section 6), and the hygiene rules every caller follows (section 7). On the Agent-tool path, call the Agent tool with:
subagent_type:Plan;model:fable;run_in_background:false;description:Plan <short task name>.effort: the step 1 tier, passed explicitly when the Agent tool's schema exposes aneffortproperty. When it does not, dispatch without it; when the check is inconclusive and the call fails input validation on that parameter, re-dispatch once without it. A dispatch withouteffortis a degradation to report in step 5, never a step failure.prompt: everything needed to plan alone: the full task, the issue title and body when fetched, the working directory, and the user's constraints. Instruct it to:- Produce a concrete, ordered plan: files to create or modify, approach, build sequence, risks and edge cases, verification.
- Number the implementation steps (
1.,2., ...) and end each with a verify point: the observable check that proves the step is done (a command, a passing test, a file state). Builders mirror these steps into their task tracker. - Plan the absolute-best solution; only correctness and safety override "best".
- Return the plan as its final message in clean Markdown, fit to post verbatim as an issue comment.
- Make no file edits and no commits, including through Bash (
fable-dispatchsection 7).
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 Changed · -28 lines 484d382254bb
- 3d ago Changed 9dbad120724f
- 5d ago Changed · -12 lines · +4 tokens per session 6bdfdace8a4a
- 9d ago First seen · 114 lines · 105 tokens per session scan A d6d2e82da657
fableplan is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 1,613 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 2026-08-30.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
arming-thought
A Chinese-language routing guide built around checking facts before drawing conclusions. It helps select other methods for tasks such as investigation, decision-making, review, and long-term planning.