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 burin-labs/harn --skill workflow-authoringgit clone --depth 1 https://github.com/burin-labs/harnWrote 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/burin-labs/harn/workflow-authoring)<a href="https://agentmods.dev/skills/burin-labs/harn/workflow-authoring"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/workflow-authoring.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.03257 |
| Opus 5 | $0.00036 | $0.01629 |
| Sonnet 5 | $0.00015 | $0.00651 |
| Haiku 4.5 | $0.00007 | $0.00326 |
Grade B, and why
workflow-authoring scanned grade B with 1 finding 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 8d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- "Bash(harn workflow function-tools:*)" How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow authoring (Harn workflow bundles)
You are authoring a portable workflow bundle — a JSON file Harn validates, previews, and runs locally. Hosts (IDE TUI/GUI, cloud-platform importers) consume the same bundle without rewriting.
Read prompting.md in this directory before composing a response. It
defines the response sections, JSON envelope, and small-model rules. Every
recipe under recipes/ is a worked, validated example you can crib from.
What good output looks like
-
A single
<bundle>block containing valid JSON for aWorkflowBundle. -
A short
<rationale>block (≤ 5 bullets) explaining the trigger, the waitpoints, and the connector requirements. -
A
<verify>block listing the exact commands the user should run:harn workflow validate --bundle out.bundle.json --json harn workflow preview --bundle out.bundle.json --json harn workflow run --bundle out.bundle.json --json
If validation fails, read the diagnostic, edit the bundle, and re-validate. Do not invent fields or kinds — the validator's enum lists are the source of truth.
Bundle skeleton
{
"schema_version": 2,
"entrypoint": "workflows/<kebab-case-id>.harn",
"transitive_modules": [
{
"path": "workflows/<kebab-case-id>.harn",
"source_hash_blake3": "blake3:<64 lowercase hex digits>",
"harnbc_hash_blake3": "blake3:<64 lowercase hex digits>"
}
],
"stdlib_version": "<harn stdlib version>",
"harn_version": "<harn version>",
"provider_catalog_hash": "blake3:<64 lowercase hex digits>",
"tool_manifest": [],
"sbom": {
"format": "spdx-lite",
"version": "2.3",
"packages": [],
"relationships": []
},
"signature": null,
"parent_trust_record_id": null,
"id": "<kebab-case-id>",
"name": "<human label>",
"version": "1.0.0",
"triggers": [
{ "id": "<trigger-id>", "kind": "github|cron|delay|webhook|mcp|manual",
"provider": "github", "events": ["pull_request.opened"],
"node_id": "<entry-node-id>" }
],
"workflow": {
"_type": "workflow_graph",
"id": "<graph-id>",
"version": 1,
"entry": "<entry-node-id>",
"nodes": {
"<node-id>": { "id": "<node-id>", "kind": "action|waitpoint|notification",
"task_label": "<short label>" }
},
"edges": [ { "from": "<from-node-id>", "to": "<to-node-id>" } ]
},
"prompt_capsules": {
"<capsule-id>": { "id": "<capsule-id>", "node_id": "<node-id>",
"trigger_id": "<trigger-id>",
"prompt": "<self-contained continuation prompt>" }
},
"policy": {
"autonomy_tier": "shadow|suggest|act_with_approval|act_auto",
"retry": { "max_attempts": 2, "backoff": "exponential" },
"catchup": { "mode": "none|latest|all", "max_events": 1 }
},
"connectors": [
{ "id": "github", "provider_id": "github",
"scopes": ["pull_requests:read", "checks:read"],
"setup_required": true, "status_required": true }
],
"environment": {
"repo_setup_profile": "default",
"worktree_policy": "reuse_current|new_worktree|host_managed",
"command_gates": ["make test"]
}
}
What ships with it
10 files 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.
- cases/pr-monitor.case.json 1.4 KB
- cases/pr-repair.case.json 1.8 KB
- eval.harn 7.0 KB
- prompting.md 6.2 KB
- recipes/pr-monitor-verifier-patch/patch.json 1.3 KB
- recipes/pr-monitor-verifier-patch/README.md 2.1 KB
- recipes/pr-monitor/bundle.json 2.9 KB
- recipes/pr-monitor/README.md 1.5 KB
- recipes/pr-repair/bundle.json 3.9 KB
- recipes/pr-repair/README.md 1.7 KB
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.
- 8d ago First seen · 283 lines · 73 tokens per session scan B c88df1f0958c
workflow-authoring is a skill published in the GitHub repository burin-labs/harn (20 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 3,257 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
gh-issue
Fetch a GitHub issue, create a branch, implement with TDD, and open a PR.
gh-issues
Walk over all open GitHub issues that are unassigned or assigned to the current user, and process each one via the /gh-issue skill, sequentially.
module-new
Scaffold a new Gacela module under src/php/ with Facade, Provider, and CLAUDE.md.