Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/deepklarity/harness-kitnpx agentmods add skills/deepklarity/harness-kit/hk-local-run-specWrote 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-run-spec)<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-local-run-spec"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-run-spec/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-run-spec"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-local-run-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 58 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 64 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 65 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00078 | $0.00995 |
| Opus 5.5 | $0.00031 | $0.00398 |
| Sonnet 5.5 | $0.00016 | $0.00199 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
hk-local-run-spec 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 1mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hk-local-run-spec — Spec Runner
Run the full odin spec workflow: plan, review, execute. Handles the gotchas so you don't have to remember them.
Usage
/hk-local-run-spec ../sample_specs/poem_spec.md
/hk-local-run-spec ../sample_specs/poem_spec.md --quick
/hk-local-run-spec ../sample_specs/poem_spec.md --mock
/hk-local-run-spec --exec-only a1b2
Arguments
Parse $ARGUMENTS to extract:
- spec_path (required unless
--exec-only): path to the spec markdown file - --quick: use
--quietmode (non-interactive, spinner only) - --mock: pass
--mockto exec (no backend writes) - --exec-only <task_id>: skip planning, just execute a specific task
The critical gotcha
Odin plan/exec invokes claude -p as a subprocess. It cannot run from inside another Claude Code session. Nested Claude Code calls fail silently or hang.
This skill detects the nested session and provides the user with copy-paste commands instead of trying to run them directly.
Execution
Step 1: Detect environment
Check if we're inside a Claude Code session:
# Claude Code sets this env var when running
echo "${CLAUDE_CODE_ENTRYPOINT:-not_set}"
If we're inside Claude Code (the var is set or we detect we're in an agent context), we cannot run odin plan/exec directly. Instead, provide copy-paste commands.
Step 2: Resolve paths
REPO_ROOT=$(git rev-parse --show-toplevel)
WORK_DIR="$REPO_ROOT/odin/temp_test_dir"
Check that temp_test_dir/ exists and has a .env:
ls "$WORK_DIR/.env" 2>/dev/null
If missing, tell the user:
temp_test_dir/ not found or missing .env.
Create it: cd odin && mkdir -p temp_test_dir && cp .env.example temp_test_dir/.env
Then edit temp_test_dir/.env with your ODIN_ADMIN_USER and ODIN_ADMIN_PASSWORD.
Step 3: Generate commands
Build the commands based on arguments:
Plan phase (skip if --exec-only):
cd "$WORK_DIR" && odin plan <spec_path> --quiet
If --quick was passed, use --quiet (which implies --auto). Otherwise default to --auto for non-interactive execution.
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.
- 1mo ago First seen · 125 lines · 78 tokens per session scan A e5247895acc1
hk-local-run-spec is a skill published in the GitHub repository deepklarity/harness-kit (102 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 995 once invoked, about $0.0003 per session on Opus 5.5. 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
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder.
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm.