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/jjilli/fable-flow/grillingnpx skills add jjilli/fable-flow --skill grillinggit clone --depth 1 https://github.com/jjilli/fable-flowWhat 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 | $0.00105 | $0.00421 |
| Opus 5 | $0.00053 | $0.00211 |
| Sonnet 5 | $0.00021 | $0.00084 |
| Haiku 4.5 | $0.00011 | $0.00042 |
Grade A, and why
grilling 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.
What it actually says
Grilling
Invoke this only when the user explicitly asks to be grilled (or to grill the plan/design). It is intentionally heavier than normal clarification — a relentless interview, not a few questions. If the user hasn't asked for it, don't start it.
When they have:
Interview the user relentlessly about every aspect of this plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one by one. For each question, provide your recommended answer.
Ask the questions one at a time, waiting for feedback on each before continuing. Asking multiple questions at once is bewildering.
If a fact can be found by exploring the codebase, look it up rather than asking — spend the user's attention only on decisions. The decisions are theirs: put each one to them and wait for the answer.
Do not enact the plan until the user confirms you have reached a shared understanding.
In this pipeline, grilling sits before /fable-flow:plan — it hardens the
task and its design decisions so the architect plans against a settled intent
rather than guesses. Once grilling ends in a shared understanding, feed the
resolved decisions into the task (.fable-flow/task.md) and proceed to planning.
Adapted from Matt Pocock's grilling skill — https://github.com/mattpocock/skills/blob/main/skills/productivity/grilling/SKILL.md
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 First seen · 37 lines · 105 tokens per session scan A ae312c872789
grilling is a skill published in the GitHub repository jjilli/fable-flow (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 421 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 2026-08-31.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
hedging-strategy
Hedging strategy design (beta hedge / option protection / tail risk / cross-asset hedging), including hedge-ratio calculation and cost evaluation.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.