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/josix/agent-flow/explaingit clone --depth 1 https://github.com/josix/agent-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 | $0.00044 | $0.01808 |
| Opus 5 | $0.00022 | $0.00904 |
| Sonnet 5 | $0.00009 | $0.00362 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade B, and why
explain 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 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
$PHASE2_OUTPUT Instructions: How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Command
Generate an interactive HTML explainer for a codebase topic. Riko gathers the relevant code scope, Senku designs a 3–5 screen teaching arc, Speedwagon authors the module brief and HTML fragment, and the assembler concatenates everything into explain-out/index.html — a file you can open directly in a browser.
Requires .claude/deep-dive.local.md (run /deep-dive first). The graphify knowledge graph (graphify-out/graph.json) is used if present; absent it degrades gracefully.
Argument Parsing
$ARGUMENTS is the raw argument string passed to this command.
- If
$ARGUMENTSis empty → print usage error and stop:Usage: /agent-flow:explain <topic> Example: /agent-flow:explain how does orchestration work Run /deep-dive first if you haven't already. - If
$ARGUMENTSstarts with--revise→ revise mode: extract the slug from the argument (e.g.--revise orchestration-pipeline) and skip Phase 1–2 if the brief exists. - Otherwise → normal mode:
$ARGUMENTSis the full topic string.
Slug derivation (compute once, use throughout all phases):
slug=$(echo "$ARGUMENTS" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd 'a-z0-9-' | cut -c1-40)
Precondition Checks
Run these checks before dispatching any agents:
if [[ ! -f ".claude/deep-dive.local.md" ]]; then
echo "Error: .claude/deep-dive.local.md not found."
echo "Run /deep-dive first to build the codebase context."
exit 1
fi
if [[ ! -f "graphify-out/graph.json" ]]; then
echo "Note: graphify-out/graph.json not found. Continuing in degraded mode (no graph context)."
fi
Phase 1 — Scope (Riko)
Dispatch Riko with this prompt template, substituting $ARGUMENTS for TOPIC and the actual content of .claude/deep-dive.local.md for DEEP_DIVE_CONTEXT:
TOPIC: $ARGUMENTS
You are gathering code scope for a topic explainer. Your output will be consumed by
Senku (curriculum design) and Speedwagon (HTML authoring) — keep it structured.
Steps:
1. Read .claude/deep-dive.local.md for architecture context.
2. If graphify-out/graph.json exists, query for nodes related to the topic.
3. Identify 3–8 file:line refs directly relevant to the topic (concrete functions,
types, or config values — not just filenames).
4. Identify 2–4 graph node names (or write "graph: unavailable" if graph absent).
5. Extract 3–6 key terminology terms specific to this topic.
Return structured markdown in exactly this format:
## Scope Bundle: $ARGUMENTS
### File References
- <file>:<start>-<end> — <one-line description>
...
### Graph Nodes
- <node-name>
... (or: graph: unavailable)
### Key Terminology
- <term>: <definition>
...
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 · 199 lines · 44 tokens per session scan B c49edb9f0b48
explain is a command published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 1,808 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
hire-debrief
Run the post-loop decision debrief — facilitator script for the 45-60 minute session. Surface inter-rater drift, anchor every claim to the rubric, name bias patterns out loud, render the hire-or-no-hire decision per the pre-committed rule, and capture learning for the next loop. Structured scores submitted BEFORE…
handover
End-of-session handover with wisdom capture. Writes status + reflections to docs/ops/, Starlight Vaults, and optionally GitHub.
lavra-checkpoint
Save session progress by filing beads, capturing knowledge, and syncing state.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
tutorial
Command "tutorial" from usurahi-project/usurahi, covering /tutorial, すること, 案内する要点 and 出力方針.
pm-crystallize
Promote a project-local lesson to /.great-pm/decisions.md (cross-project memory) when it has 3+ hits with high confidence. Surfaces candidates as PROPOSALS — never auto-promotes; human approval required.