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/sliday/harn/initnpx skills add sliday/harn --skill initgit clone --depth 1 https://github.com/sliday/harnWhat 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 | $0.00059 | $0.02949 |
| Opus 5 | $0.00030 | $0.01474 |
| Sonnet 5 | $0.00012 | $0.00590 |
| Haiku 4.5 | $0.00006 | $0.00295 |
Grade A, and why
init scanned grade A with 2 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
> These are opt-in. Run any command to add it. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r"curl\s+.*\|\s*(?:sudo\s+)?(?:bash|sh)", How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Init v2.0 — Full Project Scaffold
You are scaffolding a complete harness for the current project. Follow these steps exactly.
Step 0: Pre-flight Checks
Before anything:
-
Verify core dependencies are available:
jq— runcommand -v jqpython3— runcommand -v python3If either is missing, tell the user to install them first and stop.
-
Check if
AGENTS.md,scripts/harness/, or.claude/settings.jsonalready exist in the project root. -
If ANY exist, assess each file against the templates in this skill:
- Read each existing file
- Compare to the template version (Steps 2-6)
- Classify each as:
up-to-date,outdated(missing sections/patterns), orcustomized(user modifications beyond template)
-
Present a summary table and recommendation:
Existing harness assessment: | File | Status | Action | |-------------------------|-------------|--------------| | AGENTS.md | up-to-date | skip | | security_guard.py | outdated | update | | quality_gate.sh | customized | skip (manual)| | trace_logger.sh | missing | create | | .claude/settings.json | up-to-date | skip | Recommendation: Update 1 file, create 1 file. 2 files unchanged. Proceed?up-to-date→ skip (no changes needed)outdated→ recommend update (template has improvements)customized→ skip and flag for manual review (don't overwrite user work)missing→ create
Wait for user confirmation before proceeding. Only touch files marked for update/create.
-
If NO harness files exist, proceed directly to Step 1 (fresh scaffold).
Step 1: Detect Tech Stack
Read the project root to identify the stack:
package.json→ Node.js/TypeScript (check fortypescriptdep → TS)Cargo.toml→ Rustgo.mod→ Gopyproject.tomlorrequirements.txt→ PythonGemfile→ Ruby
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 · 379 lines · 59 tokens per session scan A 37df72a747cd
init is a skill published in the GitHub repository sliday/harn (5 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,949 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.