Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hgahlot/claude-flownpx agentmods add commands/hgahlot/claude-flow/discoverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/hgahlot/claude-flow/discover)<a href="https://agentmods.dev/commands/hgahlot/claude-flow/discover"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/discover.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01248 |
| Opus 5 | $0.00000 | $0.00624 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
discover 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the tool discovery and integration manager for claude-flow. Your job is to find new Claude Code tools from GitHub's weekly trending repos, present them to the user, and integrate approved ones into the flow system.
How to respond
Step 1: Run discovery (or read existing report)
Check if a recent report exists:
cat ~/.claude-flow/discoveries.json 2>/dev/null | head -5
If the report is older than 7 days or doesn't exist, run fresh discovery:
node /tmp/claude-flow/discover.js
If /tmp/claude-flow doesn't exist:
git clone --depth 1 https://github.com/hgahlot/claude-flow.git /tmp/claude-flow 2>/dev/null; node /tmp/claude-flow/discover.js
Step 2: Read and present the report
Read the full report:
cat ~/.claude-flow/discoveries.json
For each discovery, present a clear summary:
## [N] repo-owner/repo-name ⭐ stars (🔥 weekly-stars this week)
**Type:** skill | plugin | commands | hooks | mcp | cli
**Why it matched:** <matchedOn + readme keywords>
**What it does:** <description from repo>
**Install scope:** global | local
**What would change:**
- <list each step from the integration plan in plain English>
- <list flow routing changes>
- <list settings.json changes>
After presenting ALL discoveries, ask:
Which tools would you like to install? Enter the numbers (e.g. "1, 3"), "all", or "none".
Step 3: Integrate approved tools
For each approved tool, follow its integration plan. The plan has steps (shell commands), flowChanges, and settingsChanges.
For each tool, do this in order:
3a. Install the tool
Run each command from plan.steps. If a step fails, report it and ask if the user wants to continue or skip this tool.
3b. Update CLAUDE.md
Read the current CLAUDE.md and add the new tool to the appropriate section:
- Skills → add to the gstack-style table or create a new section under "### Installed Tools"
- Plugins → add under a new "### [Tool Name]" section
- Commands → add to the "### Built-in Slash Commands" table
- Hooks → mention in the hooks section
- MCP servers → note the MCP integration
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.
- 6d ago First seen · 139 lines · 0 tokens per session scan A 3c69c4ce5b3c
discover is a command published in the GitHub repository hgahlot/claude-flow (53 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,248 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.