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-diagnosticsgit 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-diagnostics)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-diagnostics"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-diagnostics/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-diagnostics"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-diagnostics.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 | $0.00037 | $0.01529 |
| Opus 5 | $0.00018 | $0.00764 |
| Sonnet 5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
harn-diagnostics 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harn diagnostics
Use this skill when changing errors, warnings, explain output, repair metadata,
or fix application behavior. Use it also when you need to look up what a
HARN-<CAT>-<NNN> code means.
Pair it with [[harn-language]] for syntax and type contracts and [[harn-agent]] for autonomy gating.
Code index (look up any HARN-* code)
Every diagnostic harn check, harn lint, and harn fmt emit carries a stable
HARN-<CAT>-<NNN> code. The code registry is the single source of truth. It is
crates/harn-parser/src/diagnostic_codes.rs, plus the per-code explanation in
crates/harn-parser/src/diagnostic_codes/explanations/<CODE>.md. Everything
below is generated from it, so never hand-maintain a parallel list.
- Look up one code:
harn explain HARN-TYP-014(human-readable) orharn explain HARN-TYP-014 --json(structured: category, summary, repair, safety class, related codes). - Full index of every code:
harn explain --catalog(add--format markdownor--format json). This is the complete cheat sheet — one entry per code with its summary, repair, and safety class. - Committed artifacts (kept in sync by CI):
docs/src/diagnostics.md— the rendered index, grouped by category.docs/diagnostics-catalog.json—schemaVersion: 1structured contract consumed by downstream tooling (IDE diagnostic panels, hosted error pages). Tools should read this, not regex prose.
- Regenerate after changing the registry or an explanation:
make sync-diagnostics-catalog(CI guard:make check-diagnostics-catalog).
The category prefixes below are the mental map for the index; harn explain
resolves any individual code.
Start here
- Parser diagnostics live primarily in
crates/harn-parser/. - Typechecker diagnostics live in
crates/harn-parser/src/typechecker/. - Lint diagnostics live in
crates/harn-lint/. - CLI rendering and
harn explainlive undercrates/harn-cli/src/commands/. - Repair planning and apply flows live under
crates/harn-cli/src/commands/fix.rs. - Conformance
.errorfixtures are the executable spec for intentional failures. - LSP diagnostics should derive from the same core metadata as CLI diagnostics.
- Do not fork diagnostic meaning between CLI, LSP, and docs.
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 · 137 lines · 37 tokens per session scan A 986f49b7191d
harn-diagnostics is a skill published in the GitHub repository burin-labs/harn (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,529 once invoked, about $0.0002 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
archestra-dev-investigate
Use when investigating Archestra bugs or incidents — staging issues, backend 50x errors, Drizzle failed queries, DB connection pressure, deploy regressions, or Kubernetes/runtime symptoms. Orientation only; defers the process to /investigate.
mcp-cli
Use when running, automating, integrating, or troubleshooting the MCP CLI (mcpa | mcp-ts), including local or remote discovery, authentication, schema inspection, tool calls, and gateway lifecycle errors.
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.