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.
git clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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/commands/juanmarchetto/agent-skills/runs)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/runs"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/runs/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/commands/juanmarchetto/agent-skills/runs"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/runs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00018 | $0.00478 |
| Opus 5 | $0.00009 | $0.00239 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
runs 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 6d 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.
What it actually says
/runs -- Browse Run History
You are the Post-Run Analysis skill's history browser. The user has triggered /runs to review their run history.
Instructions
-
Load run history from the project's memory. Check these locations in order:
.claude/run-history.md- MEMORY.md (look for a "Run History" section)
- Any file matching
run-history*orruns*in the project
-
If no history is found, tell the user: "No run history found. Run
/analyzeafter your next build, test, or migration to start tracking." -
Display the full history table:
## Run History | # | Date | Target | Duration | Pass/Fail | Key Metric | Delta | |---|------|--------|----------|-----------|------------|-------| | ... | ... | ... | ... | ... | ... | ... | -
Show trend analysis per target:
- Group runs by target
- For each target with 3+ runs, show the trend: improving / regressing / stalled
- Highlight the best and worst runs
-
Show summary statistics:
### Summary - Total runs tracked: N - Targets: [list of unique targets] - Overall pass rate: X% - Best run: #N ([target], [date]) -- [why it was the best] - Worst run: #N ([target], [date]) -- [why it was the worst] - Current streak: [N passes/fails in a row] -
If the user provides arguments (e.g.,
/runs test-suiteor/runs last 5):- Filter by target name if a target is specified
- Limit to last N runs if a number is specified
Important
- Present data cleanly -- tables should be aligned and readable
- Always note if history is sparse (fewer than 3 runs) -- trends are unreliable with little data
- Do not modify history -- this command is read-only
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.
- 6d ago First seen · 53 lines · 18 tokens per session scan A ae7e80291014
runs is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 478 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 2026-09-03.
Other commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).