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/packmindhub/packmind/claudegit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/claude)<a href="https://agentmods.dev/commands/packmindhub/packmind/claude"><img src="https://agentmods.dev/badge/commands/packmindhub/packmind/claude.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 | $0.00000 | $0.00357 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00071 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
CLAUDE 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.
What it actually says
Commands Package
The "commands" domain — multi-step coding commands, their versions, and their deployment.
This package was renamed from recipes
The rename was never carried through the internals, so the same concept has two names depending on where you look. Expect this rather than treating it as a bug:
- Types and public API use
Command*—Command,CommandVersion,createCommandId,CommandService,CommandVersionService,CommandSchema,commandsSchemas,CommandsHexa,CommandsAdapter. - Internals still say "recipe" — local variables, logger origins (e.g.
const origin = 'RecipeService'insrc/application/services/CommandService.ts), log messages, and TypeORM relation names such asinverseSide: 'recipe'insrc/infra/schemas/CommandSchema.ts. @packmind/recipes/testis still aliased topackages/commands/test/index.tsintsconfig.base.json, alongside@packmind/commands/test.
Rules
- Do not opportunistically rename the residue. It reaches into schemas, relation names and other packages; a partial rename breaks persistence in ways tests will not catch.
- When editing an existing file, match the names already in it. Use
Command*for anything new. - When searching this domain, grep for both spellings —
grep -i recipefinds call sites thatgrep Commandmisses.
Shared package conventions (env tags, layout, /test subpath, branded IDs): ../CLAUDE.md
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 · 29 lines · 0 tokens per session scan A cfe914b9b4be
CLAUDE is a command published in the GitHub repository PackmindHub/packmind (308 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 357 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 2026-09-03.
Other commands, from other repositories
octo-plan
Intelligent plan builder - creates strategic execution plans (doesn't execute). Use /octo:embrace to execute plans.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
cycle-start
Activate a cycle and start implementing its stories.
story-archive
Move a story from a cycle back to the backlog.
go
You are the Project Kickstart agent. Your job is simple: find PRDs, validate them, and execute the full implementation pipeline.
plan
Hierarchical planning entry point — all 11 plan verbs in one command. v3.7.2 consolidates /aura-frog:plan- (10 commands) into a single dispatcher that routes via the plan-orchestrator skill. The legacy plan- aliases still work as thin stubs.