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 skills add chhuax/praxis-devos --skill skillgit clone --depth 1 https://github.com/chhuax/praxis-devosWrote 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/skills/chhuax/praxis-devos/skill)<a href="https://agentmods.dev/skills/chhuax/praxis-devos/skill"><img src="https://agentmods.dev/badge/skills/chhuax/praxis-devos/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chhuax/praxis-devos/skill"><img src="https://agentmods.dev/badge/skills/chhuax/praxis-devos/skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00434 |
| Opus 5.5 | $0.00005 | $0.00174 |
| Sonnet 5.5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
release-kit 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 2mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release-kit
This is a maintainer-only skill entry for the in-repo release-kit/ boundary.
Use this skill only after the intended code is already merged to main.
Modes
- verify / publish / release
verifypublishrelease
Input collection rules
Before running any mode, collect and confirm:
- target version from
package.json - explicit release order confirmation
- whether the user wants the normal path or a compensation path
Default controlled order in v1:
verifypublishrelease
Do not continue to publish or release if the release order is not explicitly confirmed.
Mode responsibilities
verify
Collect:
- target version
- current repository root / worktree context
- confirmation that the user wants to prepare the release candidate
Delegate deterministic execution to release-kit/scripts/verify.mjs.
publish
Collect:
- target version
- confirmation that verified state already exists and is still valid
- confirmation that the approved order is
verify -> publish -> release
Delegate deterministic execution to release-kit/scripts/publish.mjs.
release
Collect:
- target version
- confirmation that publish/tag already completed, or that the user wants the compensation path
- confirmation that GitHub Release creation is intended now
Delegate deterministic execution to release-kit/scripts/release.mjs.
Responsibilities
- Collect the target version and release-order confirmation
- Keep the execution flow constrained to the approved release workflow
- Delegate all deterministic execution to repo scripts under
release-kit/scripts/ - Route normal and compensation paths without embedding release logic here
Constraints
- Supports Node/npm + git + GitHub only in v1
- Not part of the projection system
- Must not implement high-risk release commands directly in this file
- Must not replace explicit user confirmation for release order
- Must not perform
npm,git, orghrelease mutations directly from the skill body
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.
- 2mo ago First seen · 81 lines · 13 tokens per session scan A 065cbaedbcac
release-kit is a skill published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 434 once invoked, about $0.0001 per session on Opus 5.5. 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.
release-kit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-kitchhuax/praxis-devos | Skill | 21 | 6mo ago | Apache-2.0 | A | 13 | Claude Code, Codex |
| release-announcementpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 42 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 114k | yesterday | Apache-2.0 | A | 13 | Claude Code |
| release-notesphuryn/pm-skills | Skill | 28k | 8d ago | MIT | A | 57 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | yesterday | Apache-2.0 | A | 22 | Claude Code, Codex |