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 deepklarity/harness-kit --skill hk-local-logsgit clone --depth 1 https://github.com/deepklarity/harness-kitWrote 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/deepklarity/harness-kit/hk-local-logs)<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-local-logs"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-logs/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/deepklarity/harness-kit/hk-local-logs"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-logs.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 | $0.00130 | $0.02374 |
| Opus 5 | $0.00065 | $0.01187 |
| Sonnet 5 | $0.00026 | $0.00475 |
| Haiku 4.5 | $0.00013 | $0.00237 |
Grade A, and why
hk-local-logs 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hk-local-logs — Log Inspector & Error Debugger
Read the right log for the right problem, from the right place. No more guessing which of 5 log locations to check.
Quick Reference
| Symptom | Log to check | Command |
|---|---|---|
| 500 error, API broken | Backend | /hk-local-logs backend |
| UI not loading, build error | Frontend | /hk-local-logs frontend |
| Task not executing, queue stuck | Celery | /hk-local-logs celery |
odin plan/odin exec failed |
Odin | /hk-local-logs odin |
| Specific task execution trace | Task | /hk-local-logs task <id> |
| Migration error on startup | Backend | /hk-local-logs backend --search migrate |
| Don't know where the error is | Auto | /hk-local-logs (no args) |
Arguments
Parse $ARGUMENTS to extract:
- layer (optional):
backend,frontend,celery,odin, ortask - id (required for
task): task ID or prefix - --lines N (optional, default 50): how many lines from the end to show
- --search (optional): grep for a pattern in the log
If no layer is specified, run auto-detect mode — check all logs for recent errors.
Log Locations
All paths are relative to REPO_ROOT (use git rev-parse --show-toplevel).
| Layer | File | Format | Notes |
|---|---|---|---|
| backend | .dev-logs/backend.log |
Plain text | Django runserver stdout/stderr |
| frontend | .dev-logs/frontend.log |
Plain text | Vite dev server output |
| celery | .dev-logs/celery.log |
Plain text | Celery worker + beat |
| backend-app | taskit/taskit-backend/logs/taskit.log |
Structured plain text | App-level logging, [timestamp] LEVEL [file:line] - msg |
| backend-detail | taskit/taskit-backend/logs/taskit_detail.log |
Plain text | Full tracebacks (check here for exception details) |
| odin-runs | .odin/logs/run_*.jsonl (in working dir) |
JSON lines | Structured orchestration log |
| odin-app | .odin/logs/odin.log (in working dir) |
Plain text | Odin CLI logging |
| odin-detail | .odin/logs/odin_detail.log (in working dir) |
Plain text | Full tracebacks from odin (odin logs debug) |
| task-output | .odin/logs/task_<id>.out (in working dir) |
Plain text | Raw agent stdout for a task (odin logs <id> -f) |
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 · 221 lines · 130 tokens per session scan A d62fcd5294ce
hk-local-logs is a skill published in the GitHub repository deepklarity/harness-kit (96 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 2,374 once invoked, about $0.0006 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
neuron-debugger
Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
debug-manual
Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist.
debug-auto
Auto debug loop — investigate, fix, verify using agent-dispatched pipeline.
debug
Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation).
neuron-debugger
Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…