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 commands/jjilli/fable-flow/implementgit 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 | $0.00042 | $0.00558 |
| Opus 5 | $0.00021 | $0.00279 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
implement 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch: !
git branch --show-current - Working tree: !
git status --porcelain | head -20
Your job
Run the Implement and Merge phases of the fable-flow pipeline from the saved plan.
Input: $ARGUMENTS (--base REF overrides the plan's base)
Preconditions: .fable-flow/plan.md exists (otherwise stop and point the user at /fable-flow:plan), and the working tree is clean (otherwise stop and tell the user what's uncommitted — never stash or discard their work yourself).
- Read the plan.
BASE_SHA= the plan's recorded base (or--base).SLUG= from.fable-flow/task.md, else derive from the plan title. - Spawn one
fable-flow:implementerper track, all in a single message so they run concurrently — each already gets its own isolated worktree. Each prompt carries, inline: its full track manifest, the entire Contracts section, the conventions digest (.fable-flow/explore-conventions.md), any relevant lessons from.fable-flow/memory/lessons/(worktree subagents can't read.fable-flow/themselves),BASE_SHA, and branch slugfable-flow/<SLUG>-t<n>. Remind it: reset toBASE_SHAfirst, touch only owned files, commit before reporting. Save reports to.fable-flow/track-<n>-report.md. - Merge:
git checkout -b fable-flow/<SLUG> <BASE_SHA>, thengit merge --no-ffeach track branch in the plan's merge order. Conflicts resolve in favor of the plan's Contracts. Run the plan's Integration verification commands; fix small breakage directly, or spawn an implementer with a fix manifest based on the integration branch's current SHA for anything larger. - Clean up merged track worktrees (
git worktree remove, paths from the reports) and delete mergedfable-flow/<SLUG>-t*branches.
Report with evidence: branch, tracks merged, the actual verification output, any deviations the implementers recorded, and anything blocked. If tests fail, say so with the output — don't proceed silently. Point the user at /fable-flow:review as the next step.
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 · 26 lines · 42 tokens per session scan A d3c6c3442fd0
implement is a command published in the GitHub repository jjilli/fable-flow (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 558 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 commands, from other repositories
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
lavra-work-teams
Work on multiple beads with persistent worker teammates that self-organize through a ready queue.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).
lavra-import
Import a markdown plan into beads as an epic with child tasks.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
youtube-pulse
Summarize latest videos from tracked YouTube channels and extract short-term investment signals relevant to current holdings. Run after /market-pulse for context, or standalone for a quick opinion check.