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 harn-languagegit 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/harn-language)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-language"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-language/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/burin-labs/harn/harn-language"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.02030 |
| Opus 5 | $0.00013 | $0.01015 |
| Sonnet 5 | $0.00005 | $0.00406 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
harn-language 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 9d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harn language
Use this skill when writing, reviewing, or explaining .harn source code.
Pair it with [[harn-testing]] for fixtures and [[harn-diagnostics]] for user-facing errors.
Start here
- Read
docs/llm/harn-quickref.mdbefore editing.harnfiles. - In a Harn worktree, run
make setuponce and useHARN_BIN_NO_BUILD=1 ./scripts/harn_bin.sh -- <command>for narrow CLI checks. This resolves the lane-local binary without starting a hidden Cargo build. Outside the repository, use the installed, pinnedharnexecutable. - Use
docs/llm/harn-triggers-quickref.mdwhen trigger manifests are involved. - Read
spec/HARN_SPEC.mdas the assembled language reference. - Default new script entrypoints to
fn main(harness: Harness) { ... }and route side effects throughharness.*. - Use
harness.fs.mkdtemp_in_workspace(prefix?)for scratch files that must be visible under sandbox policy; avoid composing.harn/tmppaths by hand. - Use typed
std/fsconditional replacement for shared state or artifacts that must not overwrite a newer observation; branch on the closed receipt. - Use bounded
std/jsonlpages for file-backed logs and transcripts. Apply aSchemaContract<T>when consumers need typed records and named rules. - For connector credentials, read canonical ids such as
provider/access-tokenthroughharness.secretsfrom a package script; the runner scopes the default provider from the nearestharn.toml. - Edit the authoritative chapters under
spec/chapters/*.mdfor spec changes; never hand-edit the generatedspec/HARN_SPEC.mdordocs/src/language-spec.mdprojections. - Regenerate and verify every spec projection with
make sync-language-spec. - Check user-visible behavior with conformance fixtures under
conformance/tests/. - Keep examples small enough for agents to copy without hidden setup.
- Prefer existing syntax and stdlib helpers over new host-side shortcuts.
- Put platform spellings, policy rows, and other closed configuration in one typed data-only module. Import that value into the evaluator and mechanically project it downstream instead of duplicating lists or host branches.
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.
- 9d ago First seen · 170 lines · 25 tokens per session scan A b9ed73c7b2f3
harn-language is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 2,030 once invoked, about $0.0001 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
module-new
Scaffold a new Gacela module under src/php/ with Facade, Provider, and CLAUDE.md.
integration-fixture
Create or validate a .test integration fixture under tests/php/Integration/Fixtures.
phel-lang
Building applications WITH Phel (Lisp that compiles to PHP). Triggers on .phel files, phel-config.php, phel CLI commands (init, run, repl, test, build), or requests to build a Phel app. Skip when working on the Phel compiler internals (use compiler-guide or phel-patterns instead).
archestra-dev-rust-napi
Use when editing Rust in this repo — the NAPI crates under platform/archestra-rs (app-runtime, image, and sandbox core/-rs crate pairs plus napi-loader, with their generated TypeScript bindings) or the standalone ai-labs Rust workspace (core/runner/cli/analyzer/dashboard) — including Rust build/test checks.
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.