Borrowing it
Nothing to install: this file belongs to acartine/foolery. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/acartine/foolery/main/.agents/skills/investigate-foolery-leases/SKILL.mdgit clone --depth 1 https://github.com/acartine/fooleryWrote 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/acartine/foolery/investigate-foolery-leases)<a href="https://agentmods.dev/skills/acartine/foolery/investigate-foolery-leases"><img src="https://agentmods.dev/badge/skills/acartine/foolery/investigate-foolery-leases/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/acartine/foolery/investigate-foolery-leases"><img src="https://agentmods.dev/badge/skills/acartine/foolery/investigate-foolery-leases.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 | $0.00079 | $0.00931 |
| Opus 5 | $0.00039 | $0.00465 |
| Sonnet 5 | $0.00016 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
investigate-foolery-leases 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 12d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Foolery Leases
Use this skill to trace Foolery runtime behavior across lease lifecycle logs, interaction/session logs, and server logs.
When To Use It
- The user asks whether a step type uses leases.
- The user wants recent examples from the last 24-48 hours.
- The user asks which agent ended a turn without calling
nextorrollback. - The user suspects a hung turn, dangling lease, or runtime mismatch between
port
3000and port3210. - The user wants likely causes, not just raw log lines.
Log Roots
- Dev runtime (
bun dev, usually port3000):.foolery-logs - Installed runtime (
next start, usually port3210):~/.config/foolery/logs
Use lsof -nP -iTCP:3000 -sTCP:LISTEN and
lsof -nP -iTCP:3210 -sTCP:LISTEN only to confirm which process is live. The
authoritative evidence is in the log roots.
Workflow
- Confirm the target repo slug and time window.
- Read
_leases/*/leases.jsonl*for lease lifecycle events. - Read per-session
*.jsonl*interaction logs forsession_start,beat_state,response, andsession_end. - If needed, read
_server/*/console.logandserver.jsonl*for child close, post-close beat state, retry, and invariant handling. - Correlate by
sessionId,beatId,knotsLeaseId, and timestamps. - Produce findings with concrete examples and likely causes.
Core Checks
1. Lease Coverage
- Find which interaction types and steps emit
lease_create_*,lease_claim_binding_check,prompt_delivered, andlease_terminate_*. - Do not assume every step or interaction uses leases. Verify by code and logs.
2. Hung Or Open Turns
Flag sessions with:
prompt_deliveredbut no matchinglease_terminate_succeeded- no
session_end - continued
responsetraffic after the last lease event
3. Completed Turns Without Progress
For each completed session with exitCode: 0:
- compare
beat_state.phase == "before_prompt"with the matchingafter_prompt - resolve the claimed step
- verify the post-exit state moved to the expected next queue state or a prior queue state
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.
- 12d ago First seen · 111 lines · 79 tokens per session scan A 5320d3e73ef9
investigate-foolery-leases is a skill published in the GitHub repository acartine/foolery (56 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 931 once invoked, about $0.0004 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
stress-test
Use when a design, plan, or decision needs adversarial scrutiny before proceeding. Interrogates every branch of the decision tree, providing recommended answers and forcing explicit agreement or pushback. Triggers on "grill me", "stress test this", "poke holes", "challenge this design", or when…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
deepthink
Use when a problem resists quick answers, debugging stalls, analysis feels shallow, confidence is low, hypotheses are competing, reasoning loops repeat, or a hard problem needs evidence tracking.
performance-analyst
Use when reviewing hot paths, slow code, database queries, N+1 risks, memory usage, loops, I/O, caching strategy, concurrency, latency-sensitive paths, or resource efficiency.
tracer
Use when tracing execution paths, mapping dependencies, understanding unfamiliar code, following data flow, investigating end-to-end behavior, debugging call chains, or deciding which files to read next.
bugfix
Diagnose and fix bugs using hypothesis-driven debugging, diagnostic instrumentation, architecture-aware analysis, and evidence-based root cause identification.