explore

A command that runs the Explore stage of the fable-flow software-development process. It asks three read-only agents to examine the codebase from different angles and save their findings for planning.

In plain words
What is it for?
Use it to investigate where a change belongs, how the project is written and tested, and what other code may be affected. It records the task and produces three reports in .fable-flow/.
Why use it?
It gathers the codebase facts needed before making a plan, reducing guesswork about structure, conventions, and possible side effects.

Command

Install

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.

agentmods
npx agentmods add commands/jjilli/fable-flow/explore
Clone the repo
git clone --depth 1 https://github.com/jjilli/fable-flow
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00287
Opus 5 $0.00019 $0.00143
Sonnet 5 $0.00008 $0.00057
Haiku 4.5 $0.00004 $0.00029

Measured yesterday against content hash 3274828b3e09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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.

commands/explore.md · 18 lines

What it actually says

Run the Explore phase of the fable-flow pipeline for this task:

Task: $ARGUMENTS

(If no task is given above, reuse the one in .fable-flow/task.md; if neither exists, ask the user for one — that's input only they can provide.)

  1. Create .fable-flow/ in the repo root if missing, add .fable-flow/ to .git/info/exclude if absent, and record the task in .fable-flow/task.md.
  2. Spawn three fable-flow:scout subagents in a single message so they run concurrently — lenses structure, conventions, and blast-radius. Each prompt: the task, its lens, the current branch.
  3. Save each digest verbatim to .fable-flow/explore-<lens>.md.

Then report: one short paragraph per lens with what matters most for planning, plus the risks and unknowns the scouts flagged. Point the user at /fable-flow:plan as the next step. Report only what the digests actually say — don't pad or speculate.

Changes

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.

  1. yesterday First seen · 18 lines · 38 tokens per session scan A 3274828b3e09

Subscribe to this mod's changes

explore is a command published in the GitHub repository jjilli/fable-flow (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 287 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.