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/hatch3r/hatch3r/hatch3r-askgit clone --depth 1 https://github.com/hatch3r/hatch3rWrote 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/hatch3r/hatch3r/hatch3r-ask)<a href="https://agentmods.dev/commands/hatch3r/hatch3r/hatch3r-ask"><img src="https://agentmods.dev/badge/commands/hatch3r/hatch3r/hatch3r-ask.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 | $0.00054 | $0.03043 |
| Opus 5 | $0.00027 | $0.01522 |
| Sonnet 5 | $0.00011 | $0.00609 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade A, and why
hatch3r-ask 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
§0 Detect Ambiguity (P8 B1)
Before any dispatch, scan the question for unresolved scope. Domain triggers: the subject matches two or more distinct subsystems ("how does caching work" in a repo with both an HTTP cache and a build cache), the question hides a change request ("how would I add SSO" wants a plan, not a description), or the expected answer shape is unstated (a one-line pointer vs an architecture walkthrough). When a trigger fires, ask ONE bundled multiple-choice clarification via the platform-native question tool per agents/shared/user-question-protocol.md — 2-4 numbered interpretations with one-line trade-offs and a declared default. Proceed without asking ONLY when the question names a single subject with a single reasonable reading. Ambiguity surfaced mid-research re-enters this gate via the researcher's BLOCKED_AMBIGUITY return.
Agent Pipeline
| Stage | Agent(s) | Parallel | Required |
|---|---|---|---|
| 1. Parse question + triage facets | Orchestrator (inline, read-only) | No | Yes |
| 2. Research | hatch3r-researcher (modes per the selection table) |
Per independent facet | Yes |
| 3. Answer synthesis + Iteration Summary | Orchestrator (inline, single writer) | No | Yes |
Parallel-safety conditions (per rules/hatch3r-agent-orchestration.md §Parallel Safety): facet researchers are read-only, findings aggregate as a deterministic union keyed by facet, and no shared mutable state exists — all three hold by construction, so multi-facet fan-out always dispatches in parallel, in a single message.
Ask — Answer a Question About This Codebase
Answers a free-form question about the repository the user is working in — "where is X handled?", "how does the auth flow work?", "what would adding multi-tenancy touch?" — with evidence-cited findings from hatch3r-researcher, mutating nothing. This is the pipeline's read-only Q&A surface: research depth scales with question breadth, and the answer states what the evidence supports, what it contradicts, and what it cannot settle.
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 · 164 lines · 54 tokens per session scan A 86187a159082
hatch3r-ask is a command published in the GitHub repository hatch3r/hatch3r (26 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 3,043 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
fixlinks
Find replacement URLs for broken links using research agents.
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
examples
Real-world examples and scenarios for pair programming sessions.
flow-nexus-user-tools
User management, storage, and system utilities.
post-task
Execute post-task cleanup, performance analysis, and memory storage.
token-efficiency
Reduce token consumption while maintaining quality through intelligent coordination.