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 fable-new-issuegit 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/fable-new-issue)<a href="https://agentmods.dev/skills/richkuo/rk-skills/fable-new-issue"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-new-issue/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/fable-new-issue"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/fable-new-issue.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 | $0.00107 | $0.01436 |
| Opus 5 | $0.00053 | $0.00718 |
| Sonnet 5 | $0.00021 | $0.00287 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade B, and why
fable-new-issue scanned grade B with 1 finding 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 6d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
3. Any other install location — search by name, e.g. `ls ~/.claude/plugins/*/skills/new-issue/SKILL.md` (plugin-marketplace installs live under a plugin directory, not `~/.claude/skills/`). How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-new-issue
Delegate issue drafting to a Fable 5.1 subagent, then file it from the main agent. The subagent only researches and composes — it never files, edits files, or posts to GitHub; the main agent handles filing and all follow-on actions.
Input
Same as new-issue:
- A description of the bug/feature/task to file.
- Nothing — derive from the current conversation. Since the subagent can't see this conversation, the main agent first writes a faithful summary of the discussed bug/design/follow-up (with any file paths or symbols already named) to a scratchpad file and hands that path to the subagent as the source description.
- Optionally
owner/repoor a repo path when the issue belongs elsewhere.
Steps
1. Resolve the drafting procedure
Locate the new-issue SKILL.md the subagent must follow — prefer the project-local copy over the global one:
<repo>/.claude/skills/new-issue/SKILL.md(if it exists)~/.claude/skills/new-issue/SKILL.md- Any other install location — search by name, e.g.
ls ~/.claude/plugins/*/skills/new-issue/SKILL.md(plugin-marketplace installs live under a plugin directory, not~/.claude/skills/).
Record the absolute path. If none of these resolves, stop and tell the user.
If the input is conversation-derived, write the scratchpad summary now (see Input). Do NOT pre-research or pre-draft the issue yourself — the subagent owns steps 1–6 of the procedure up to (but not including) the gh issue create call.
2. Dispatch the Fable 5.1 drafting subagent
Load the fable-dispatch skill before dispatching: it owns the dispatch path and the dispatch-hygiene rules in its section 7 (read-only prompt, snapshot/diff, retry once then report). Dispatch per its ladder; on the Agent-tool path, call the Agent tool with:
subagent_type:Plan(read-only: no Edit/Write, keeps drafting side-effect-free)model:fable(the whole point — the draft must come from Fable 5.1)run_in_background:false— filing depends on the draftdescription:Draft issue: <short topic>prompt: hand it everything needed to draft independently:- The user's description verbatim (or the scratchpad summary path), the working directory, and the target repo if not the current checkout.
- Instruct it to read the SKILL.md at the recorded path and execute its steps 1 through 6 exactly — repo/duplicate check, claim grounding with
file:linecitations traced against the correct baseline, approach design, complexity score, scope check, and full body composition per the step-6 template. - It must STOP before filing: no
gh issue create, nogh issue edit, no comments posted, no file edits — state the read-only rule explicitly in the prompt perfable-dispatchsection 7. Read-onlyghcalls (gh issue list,gh pr list,gh repo view,gh label list) are expected and allowed. - Return as its final message: (a) any duplicate found (URL + why it matches) — in which case no draft; (b) otherwise the complete issue draft — exact title with
[C<score>]prefix and the full body per the template — plus one line stating which baseline claims were traced against, and any unfiled follow-up candidates from the scope check.
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.
- 6d ago Changed · +4 tokens per session 1d2eecbfda78
- 11d ago First seen · 70 lines · 103 tokens per session scan B 64a04f70bd55
fable-new-issue is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,436 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
issue-fields-migration
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say "migrate my labels to issue fields", "migrate project fields to issue fields", "convert labels to issue fields", "copy project field values to issue fields"…
flowstudio-power-automate-governance
Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load…
gtm-enterprise-account-planning
Strategic account planning and execution for enterprise deals. Use when planning complex sales cycles, managing multiple stakeholders, applying MEDDICC qualification, tracking deal health, or building mutual action plans. Includes the "stale MAP equals dead deal" pattern.
gtm-enterprise-onboarding
Four-phase framework for onboarding enterprise customers from contract to value realization. Use when implementing new enterprise customers, preventing churn during onboarding, or solving the adoption cliff that kills deals post-go-live. Includes the Week 4 ghosting pattern.
gtm-operating-cadence
Design meeting rhythms, metric reporting, quarterly planning, and decision-making velocity for scaling companies. Use when decisions are slow, planning is broken, the company is growing but alignment is worse, or leadership meetings consume all time without producing decisions.