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.
git 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-spec)<a href="https://agentmods.dev/commands/hatch3r/hatch3r/hatch3r-spec"><img src="https://agentmods.dev/badge/commands/hatch3r/hatch3r/hatch3r-spec.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 | $0.00063 | $0.04522 |
| Opus 5 | $0.00032 | $0.02261 |
| Sonnet 5 | $0.00013 | $0.00904 |
| Haiku 4.5 | $0.00006 | $0.00452 |
Grade A, and why
hatch3r-spec 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 3d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hatch3r-spec
Spec orchestrator that detects project state, picks the matching spec agent (hatch3r-greenfield-spec or hatch3r-brownfield-spec), and aggregates the per-state deliverable manifest — 8 deliverables greenfield, 9 brownfield: shared core (requirements, acceptance criteria, risk inventory, test plan) plus state-specific deliverables (greenfield: market/competitive/persona/tech-stack; brownfield: codebase-map/pattern-detection/integration/migration/non-destructive-check). The Deliverable Manifest below is the single source of truth for filenames and output location; both agents mirror it. Routing is mutually exclusive — exactly one spec agent runs per invocation.
Relationship to /hatch3r-project-spec
/hatch3r-spec and /hatch3r-project-spec are both greenfield entry points and overlap on business research (market, competitive analysis, personas). They are meant to run in sequence, not in parallel:
- This command produces the PRD (
docs/specs/prd.md) plus market/competitive/persona/tech-stack research — the product-requirements layer. /hatch3r-project-specproduces the technical-design tree (ADRs, domain model, per-module specs,todo.md,AGENTS.md) plus business-doc specs — the layer that consumes the PRD.
Sequence: run /hatch3r-spec first, then hand its docs/specs/ output to /hatch3r-project-spec. project-spec's Step 1 extracts vision, personas, and market context from the PRD instead of re-interviewing, and skips regenerating the market/competitive research this command already wrote. Running both from scratch re-executes the overlapping business-research fan-out and yields two unreconciled spec trees — sequence them to avoid it.
Deliverable Manifest (single source of truth)
This table is the one authoritative contract for what a spec run writes — filename, output location, and count. Both spec agents (hatch3r-greenfield-spec, hatch3r-brownfield-spec) mirror these filenames and write to the passed output_root; where an agent and this table disagree, this table wins. Agents cite this manifest rather than restating a divergent contract.
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.
- 3d ago First seen · 239 lines · 63 tokens per session scan A c272d413552f
hatch3r-spec is a command published in the GitHub repository hatch3r/hatch3r (26 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 4,522 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 2026-09-03.
Other commands, from other repositories
story-6.1.4
Story ID: 6.1.4 Epic: Epic-6.1 - Agent Identity System Wave: Wave 1 (Foundation) Status: 📋 Ready to Start Priority: 🔴 Critical Owner: Dev (Dex) Created: 2025-01-14 Updated: 2025-01-17 (v4 - Unified System Integration) Duration: 2.5 days (20 hours) Investment: $250.00.
story-7.1.1
Story ID: 7.1.1 Epic: Epic-7 - Dashboard Workspace Integration Wave: Wave 1 (Foundation) Status: ⌛ In Progress Priority: 🔴 High Owner: Architect (Aria) → Dev (Dex) Created: 2026-05-05 Updated: 2026-05-05.
maintainer-standup
Synthesize the maintainer's morning standup brief from gathered git/PR/issue/state data.
create-task-list-for-issue.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
github-epic-menu.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
phase-track.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.