Borrowing it
Nothing to install: this file belongs to anthony-chaudhary/dos-kernel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthony-chaudhary/dos-kernel/master/.claude/skills/stable-release/SKILL.mdgit clone --depth 1 https://github.com/anthony-chaudhary/dos-kernelWrote 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/anthony-chaudhary/dos-kernel/stable-release)<a href="https://agentmods.dev/skills/anthony-chaudhary/dos-kernel/stable-release"><img src="https://agentmods.dev/badge/skills/anthony-chaudhary/dos-kernel/stable-release/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/anthony-chaudhary/dos-kernel/stable-release"><img src="https://agentmods.dev/badge/skills/anthony-chaudhary/dos-kernel/stable-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 279 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00081 | $0.05089 |
| Opus 5.5 | $0.00032 | $0.02036 |
| Sonnet 5.5 | $0.00016 | $0.01018 |
| Haiku 4.5 | $0.00008 | $0.00509 |
Grade A, and why
stable-release 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stable Release — a named channel on top of rolling /release (DOS)
/release ships a rolling tag (vX.Y.Z) whenever DOS lands user-visible change.
That tag promises "this commit merged" — it does not promise "the substrate
was provably trustworthy here." This skill adds a second, less-frequent channel
that does make that promise.
A stable release is a promotion of an already-shipped commit, not a new
build. No new version is minted. No new wheel or zip is produced. The gate is
read at promote time, frozen into an evidence file, and a second annotated tag
(stable/<codename>) is pinned on the same commit.
This is the DOS adaptation of
job's stable-release skill. job gates on apply-loop hero metrics (silent-failure share, PSV verified-success rate, funnel-stage regressions) and KEEP-slot baselines fromexecution-state.yaml+baselines.yaml. None of that exists in DOS — DOS is a domain-free trust substrate, not an apply pipeline; it has no runtime funnel, no hero metric, no baseline ledger. So the gate is re-grounded on the only "known-good" signals DOS actually has: a green kernel suite, a clean truth syscall, and a soak window. See "The gate" below.
Trunk is master. The stable tag is pinned on a commit reachable from
master; the push targets master's remote.
The kernel-vs-tooling boundary. The gate context script
(scripts/stable_release_context.py) and this skill are dev/release tooling
that operates ON the package — never imported BY dos.*. The
"kernel imports no host, no scripts/" litmus in CLAUDE.md stays intact.
Relationship to other systems
| System | Owns | Stable-release reads | Stable-release writes |
|---|---|---|---|
/release (scripts/release_bump.py) |
rolling vX.Y.Z tag, version markers |
the latest vX.Y.Z as promotion candidate |
nothing — never re-bumps |
the kernel suite (pytest) |
substrate correctness | exit code (green == eligible) | nothing |
the truth syscall (dos verify) |
ground-truth adjudication | exit + verdict (well-formed == eligible) | nothing |
| git tags | the channel itself | stable/* collision check + previous-stable |
one new stable/<codename> tag |
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 · 376 lines · 81 tokens per session scan A 800057bc5c0c
stable-release is a skill published in the GitHub repository anthony-chaudhary/dos-kernel (21 stars, last pushed 10d ago), licensed MIT. It adds 81 tokens to every session and 5,089 once invoked, about $0.0003 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.
stable-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stable-releaseanthony-chaudhary/dos-kernel | Skill | 21 | 10d ago | MIT | A | 81 | Claude Code |
| codew-release-qa-sweepHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 31 | Claude Code, Codex |
| gh-credit-harvestHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 30 | Claude Code, Codex |
| releaseHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 0 | Claude Code, Codex |
| githubHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| releaserunxhq/runx | Skill | 104 | yesterday | Apache-2.0 | A | 23 | Claude Code, Codex |
| b3os-release-opsb3rys/b3rys-team-os | Skill | 17 | 3d ago | Apache-2.0 | A | 113 | Claude Code, Codex |