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/harmont-dev/harmont-cli/write-pipelinenpx skills add harmont-dev/harmont-cli --skill write-pipelinegit clone --depth 1 https://github.com/harmont-dev/harmont-cliWhat 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 | $0.00062 | $0.01317 |
| Opus 5 | $0.00031 | $0.00659 |
| Sonnet 5 | $0.00012 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
write-pipeline 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write, modify, or extend Harmont CI pipelines defined in .hm/pipeline.py. Pipelines are real Python programs that import the harmont SDK and declaratively define build steps, triggers, and caching.
When to use
- The user asks to "set up CI", "add a pipeline", "write a pipeline", or "configure Harmont"
- The user wants to add, remove, or modify pipeline steps
- The user asks to add triggers, caching, or environment variables to a pipeline
- The user wants to switch toolchains or add a new toolchain to their pipeline
- The user asks to create a multi-pipeline setup
- The user is migrating from another CI system and wants a Harmont pipeline
When NOT to use
- The user only wants to run an existing pipeline — use the
validate-ciskill instead - The user is debugging a build failure caused by their application code, not the pipeline definition
- The user asks about Harmont Cloud features (login, org management, billing)
Before you start
-
Fetch the patterns guide — the single most important reference:
WebFetch https://docs.harmont.dev/pipeline-sdk/patterns.mdRead it carefully. It covers correct vs. incorrect approaches, when to use toolchains vs. raw shell, and common anti-patterns.
-
If you need the full API reference for a specific toolchain or feature, fetch the relevant page (append
.mdto any docs.harmont.dev URL for raw Markdown):- Toolchain reference:
https://docs.harmont.dev/pipeline-sdk/reference/toolchains/<name>.md(rust, python, js, go, cmake, zig, elixir, etc.) - Chains and steps:
https://docs.harmont.dev/pipeline-sdk/reference/chains.md - Triggers:
https://docs.harmont.dev/pipeline-sdk/reference/triggers.md - Caching:
https://docs.harmont.dev/pipeline-sdk/reference/cache.md - Pipeline decorator/factory:
https://docs.harmont.dev/pipeline-sdk/reference/pipeline.md - Full page index:
https://docs.harmont.dev/llms.txt
- Toolchain reference:
-
If you need a complete working example for a language or framework:
WebFetch https://docs.harmont.dev/examples/<language>.mdAvailable examples: rust, go, cmake, zig, nextjs, python-uv, elixir
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 · 104 lines · 62 tokens per session scan A 42b59dcffa08
write-pipeline is a skill published in the GitHub repository harmont-dev/harmont-cli (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,317 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
zuke-write-build
Write or edit a Zuke build (zuke.ts) — the code-first, strongly-typed build system for Deno/TypeScript. Use when adding or changing targets, wiring dependencies, calling a tool wrapper (DenoTasks, NpmTasks, DockerTasks, ...), generating CI, or authoring/refactoring a zuke.ts build file. For first-time project…
zuke-setup
Set up Zuke — a code-first, strongly-typed build automation system for Deno/TypeScript — in a project. Use when the user wants to add Zuke to a repo, scaffold a zuke.ts build file, install the Zuke CLI, or bootstrap the ./zuke launcher. After scaffolding, switch to the zuke-write-build skill to author targets.
ci-secure
Scans a repo's GitHub Actions workflows for the ten critical CI/CD attack vectors — template injection, fork code executed with privileges (pwn requests), cache poisoning, impostor action SHAs, secrets dumps, GITHUBENV hijack, write-token untrusted triggers, credentials in caches/artifacts, unverified remote code…
skills-registry-security
Checks the third-party security audit status of a skill published to a skills registry (skills.sh) across every cached surface, decides whether a failing finding is real or points at content already removed, and drives a stale badge to green unattended. Runs a real install to capture what users see, reads the…
sling
Diagnoses GitHub Actions failures and attributes CI time and cost using StarSling's sling CLI. Invoke this BEFORE using gh or fetching any logs whenever the user asks why a job or run failed, what made a run slow, about runner minutes or CI cost, asks to re-run or cancel a run, or pastes a GitHub Actions URL — sling…
ci-score
Grades a repository's GitHub Actions configuration against CI best practices (the CI Score: eleven pass/fail configuration facts computed from the repo's own workflow YAML) and hands back concrete fixes for every gap, ranked by impact and risk, each with an apply-now option and a paste-able agent prompt. Use when: (1)…