Borrowing it
Nothing to install: this file belongs to boldblackai/harness. 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/boldblackai/harness/main/.agents/skills/release/SKILL.mdgit clone --depth 1 https://github.com/boldblackai/harnessWrote 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/boldblackai/harness/release)<a href="https://agentmods.dev/skills/boldblackai/harness/release"><img src="https://agentmods.dev/badge/skills/boldblackai/harness/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/boldblackai/harness/release"><img src="https://agentmods.dev/badge/skills/boldblackai/harness/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Agent Snooping · line 311 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 352 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- low Excessive Agency · line 10 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00110 | $0.03861 |
| Opus 5.5 | $0.00044 | $0.01544 |
| Sonnet 5.5 | $0.00022 | $0.00772 |
| Haiku 4.5 | $0.00011 | $0.00386 |
Grade A, and why
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 1mo 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill for harness
Automates the full release pipeline: pre-flight checks → version bump → CHANGELOG → build → open release PR → (maintainer merges) → CI auto-tags, publishes to npm (OIDC), creates GitHub release, builds Docker images.
npm publishing is fully automated via trusted publishing (OIDC). The agent never touches npm credentials, pushes tags, or creates GitHub releases. It only opens a release PR; merging that PR triggers a chain of workflows that handle everything:
tag-on-merge.yml— fires when a commit starting withrelease vlands on main (i.e., the squash-merged release PR). Tags the release, publishes to npm via OIDC (with provenance attestations), and creates the GitHub release — all in one workflow.docker.yml— fires on push to main. When the commit is a release (release vprefix),merge-variantproduces version-tagged images (e.g.hermes-1.9.6) in addition to SHA tags.Why one workflow, not three: GitHub Actions does not let a workflow using
GITHUB_TOKENtrigger another workflow. A separatepublish.ymltriggered by the tag push would never fire because the tag was pushed bygithub-actions[bot]. Merging npm publish intotag-on-merge.ymleliminates the cross-workflow trigger problem without needing a PAT.Release model: The trust boundary is "can merge a PR to main" = "can release." The agent has zero upstream write access — it opens the PR from its fork; the maintainer's merge triggers everything.
Prerequisite (one-time, manual on npmjs.com): Configure the trusted publisher for
@boldblackai/harnessunder Settings → Trusted Publisher → GitHub Actions: org=boldblackai, repo=harness, workflow filename=tag-on-merge.yml. Then under Settings → Publishing access, select "Require two-factor authentication and disallow tokens" (recommended) — OIDC publishes are unaffected by this setting.
Step 1: Pre-flight checks (abort on failure)
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.
- 1mo ago Changed · -4 lines 2cd1ad216897
- 2mo ago First seen · 372 lines · 110 tokens per session scan A e97395d73a41
release is a skill published in the GitHub repository boldblackai/harness (14 stars, last pushed 4d ago), licensed MIT. It adds 110 tokens to every session and 3,861 once invoked, about $0.0004 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 2026-08-31.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releaseboldblackai/harness | Skill | 14 | 4d ago | MIT | A | 110 | 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 |