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/debabsah/fable-method/fable-shipnpx skills add debabsah/fable-method --skill fable-shipgit clone --depth 1 https://github.com/debabsah/fable-methodWhat 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 | $0.00046 | $0.01541 |
| Opus 5 | $0.00023 | $0.00771 |
| Sonnet 5 | $0.00009 | $0.00308 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
fable-ship 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fable-ship
The report is part of the work, not an afterthought. Ship a calibrated claim and the docs that let a stranger redo it.
The report
- Answer first, then the support. Lead with the verdict (done / not done / exact / blocked) in the first line; put evidence underneath, never above.
- Scale the report to the tier. T1 = the verdict, its
Verified:line(s), and the tier line — a few lines, not a document. The full shape here is for T2+. - Separate verified from assumed, out loud — as the method's ledger (canonical shapes: the method skill's ledger section; same tokens every report, and the Stop-hook gate greps for them). Never let an
Assumed:line read like aVerified:one. - Cite specifics: paths, counts,
file:line, the command you ran, the number you saw, before→after deltas. - Report what you observed, not what you intended. If a step was skipped or a test failed, say so with the output.
- Calibrate "done" with a use-boundary. Stamp unproven results PROVISIONAL ("do not quote these yet") and lift it explicitly only when the check passed. Scope the claim to exactly what you measured; put the rest in a visible residual list.
- State the tier and its gates. One line:
Tier: Tn — gates run: <verify / review lenses / human gate>. A skipped gate that leaves no trace is invisible exactly when it matters. - Never soften a real problem — including your own. Flag anything the human must decide (⚠️), state it plainly with the evidence, and repeat the flag into every downstream artifact (PR body, log, memory), not just the chat.
- End with what the reader still owns. Even a perfect report leaves a short list: every
Assumed:line, plus any T3 (outward/production) action gated to the human. Say it explicitly — worry-less means a short, honest residual list, not an empty one. - Close in the reader's language: where we are, what's next. After the ledger, two plain-language lines — the state of the work, and the single next move with whose it is. No session-jargon: a label coined mid-work (a codename, a phase number, an internal shorthand) gets one plain-word gloss or stays out of the report. The reader is catching up, not replaying your process — findings go above; the ending is orientation.
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 First seen · 45 lines · 46 tokens per session scan A 14b85f5dc893
fable-ship is a skill published in the GitHub repository debabsah/fable-method (1 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,541 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 2026-08-31.
Other skills, from other repositories
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
hud
Configure HUD display options (layout, presets, display elements).
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
kelos
Author, debug, and operate Kelos resources (Task, Session, Workspace, AgentConfig, TaskSpawner) on Kubernetes. Use for Kelos CRDs, resource manifests, the kelos CLI, or live cluster operations. Do not use for ordinary Kelos repo code edits, tests, reviews, build/CI, or git tasks unless they involve those resources.
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…