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 runxhq/runx --skill run-historygit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/run-history)<a href="https://agentmods.dev/skills/runxhq/runx/run-history"><img src="https://agentmods.dev/badge/skills/runxhq/runx/run-history/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/runxhq/runx/run-history"><img src="https://agentmods.dev/badge/skills/runxhq/runx/run-history.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 | $0.00034 | $0.00530 |
| Opus 5 | $0.00017 | $0.00265 |
| Sonnet 5 | $0.00007 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
run-history 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 8d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run History
Read the local Runx ledger through the native receipt.query service and the
installed catalog through runx.skill.inspect. The runner computes the report
itself; it does not ask an agent to invent commands, launch subprocesses, or
transcribe counts.
Use it for operational questions about recent Runx activity, failed or blocked
runs, pending runs, frequently used receipt subjects, and skill entries without
fixtures or inline harness cases. Use audit-receipt or diagnose-skill-run to
inspect one suspicious run, and least-privilege when receipt-backed authority
usage is available for grant attenuation.
Evidence boundary
- Live execution reads only the native receipt and catalog projections. These services share the same store resolution, signature policy, and catalog parser as the Runx CLI without routing back through the CLI as a subprocess.
- History reads are bounded to 1,000 rows by default and 10,000 at most.
history_receipts,pending_runs, andcatalog_itemsare replay inputs for harnesses and controlled analysis.history_receiptsandcatalog_itemsmust be supplied together; replay never silently mixes caller data with live native state.- Empty history returns
needs_more_evidencerather than a healthy verdict. closed_rateis the share of terminal receipt rows whose status isclosed.refusal_ratecountsblockedanddeclinedterminal rows. It is reported as an observation, not automatically treated as a defect.- Catalog coverage is the number of native catalog entries declaring at least one fixture or inline harness case. It is not a maturity grade.
Output
history_report contains:
- the exact resolved query and source labels (
native_receipt_store,native_skill_catalog, orsupplied_replay); - terminal and pending counts, status counts, closed/refusal rates;
- the most frequent receipt subjects;
- catalog entry and test-coverage counts;
- bounded recommendations routed to
diagnose-skill-run,audit-receipt, orskill-lab harness; - limitations when native projections cannot support a stronger claim.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 53 lines · 34 tokens per session scan A cf8e8732664d
run-history is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 530 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 2026-09-03.
Other skills, from other repositories
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.