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 skills/opensource03/harnss/releasenpx skills add OpenSource03/harnss --skill releasegit clone --depth 1 https://github.com/OpenSource03/harnssWhat 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 | $0.00054 | $0.01226 |
| Opus 5 | $0.00027 | $0.00613 |
| Sonnet 5 | $0.00011 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00123 |
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 2d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harnss Release Workflow
Run the full release pipeline. Bump type is passed as $ARGUMENTS (major, minor, or patch).
Step 1: Pre-flight Checks
Run these commands and read every line of output:
git status
git diff --cached --stat
git diff --cached
If the diff is too large to read in one shot, read it in chunks (e.g., per-directory or line ranges). You must read the entire diff before proceeding.
Review for:
- Test files, scratch files, temp files, debug artifacts (e.g.,
test-*.ts,scratch.*,*.tmp,random-*.md) - Files that shouldn't be committed (
.env, credentials, large binaries)
If you find any:
- Unstage or remove them
- Tell the user what you removed
If there are no staged changes but unstaged changes exist, ask the user if they want to stage anything first. If the working tree is completely clean (nothing to release), tell the user and stop.
Step 2: Version Bump
Determine new version
- Read the current version from
package.json(the"version"field) - Get the latest tag:
git tag --sort=-v:refname | head -1 - Parse the current version as
MAJOR.MINOR.PATCH - Apply the bump type from
$ARGUMENTS:major→(MAJOR+1).0.0minor→MAJOR.(MINOR+1).0patch→MAJOR.MINOR.(PATCH+1)
- If
$ARGUMENTSis empty or invalid, ask the user which bump type they want
Check for SDK updates
npm view @anthropic-ai/Codex-agent-sdk version
Compare with the version in package.json under dependencies["@anthropic-ai/Codex-agent-sdk"] (strip the ^ prefix for comparison). If a newer version exists, update the dependency version (keep the ^ prefix) and tell the user.
Apply changes
- Edit
package.jsonto set the new version number - Stage it:
git add package.json - If the SDK was updated, also run:
pnpm install git add package.json pnpm-lock.yaml
Step 3: Commit
Choose the commit message based on what's staged:
Feature/fix changes staged (not just version bump)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 163 lines · 54 tokens per session scan A f103688b9f3b
release is a skill published in the GitHub repository OpenSource03/harnss (360 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 1,226 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 2026-08-30.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
agentmail
Use when an agent needs AgentMail CLI email inboxes.
mcporter
List, auth, and call MCP servers/tools from the terminal.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".