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-tracinggit 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-tracing)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-tracing"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-tracing/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-tracing"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-tracing.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 | $0.00026 | $0.00862 |
| Opus 5 | $0.00013 | $0.00431 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
harn-tracing 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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harn tracing
Use this skill when inspecting or changing transcripts, receipts, run records, replay, observability events, or portal-facing activity data.
Pair it with [[harn-orchestration]] for workflow events and [[harn-testing]] for deterministic replay fixtures.
Start here
- Transcript code is primarily under
crates/harn-vm/src/orchestration/. - Run-record code lives near orchestration record modules.
- Replay surfaces feed CLI audits, evals, and portal views.
- Receipts describe durable actions and decisions.
- OTel and Langfuse exporters are observability surfaces, not core logic.
- The portal UI lives under
crates/harn-cli/portal/. - Only edit portal code when the stored activity contract changes.
- Treat persisted trace data as a compatibility contract.
Transcript rules
- Preserve event ordering.
- Preserve event ids.
- Preserve cursors.
- Preserve session ids.
- Preserve run ids.
- Preserve worker lineage.
- Preserve parent-child relationships.
- Preserve private/public transcript boundaries.
- Do not leak secrets into public event channels.
- Normalize old records rather than breaking replay.
Receipt rules
- Keep receipts machine-readable.
- Keep action ids stable.
- Keep provenance fields explicit.
- Include enough context for audit.
- Avoid full private prompt content unless the receipt channel is private.
- Record approvals and denials distinctly.
- Record skipped work when it affects outcome.
- Record replay-relevant hashes when available.
- Human summaries may change more freely than JSON contracts.
- Use [[harn-diagnostics]] for receipt validation failures.
Replay rules
- Replay should not call live providers.
- Replay should not require network access.
- Replay should not depend on wall-clock time.
- Replay should preserve deterministic ordering.
- Replay fixtures should be small and explain the scenario.
- Replay failures should point to the first mismatched event.
- Cached inputs should be explicit.
- Signed timestamps should stay verifiable.
- Missing optional fields should have deterministic defaults.
- Add migration coverage for persisted schema changes.
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.
- 10d ago First seen · 103 lines · 26 tokens per session scan A e62bde1c0a9f
harn-tracing is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 862 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
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.