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 jeunessegamesee/clew --skill research-use-casegit clone --depth 1 https://github.com/jeunessegamesee/clewWrote 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/jeunessegamesee/clew/research-use-case)<a href="https://agentmods.dev/skills/jeunessegamesee/clew/research-use-case"><img src="https://agentmods.dev/badge/skills/jeunessegamesee/clew/research-use-case/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/jeunessegamesee/clew/research-use-case"><img src="https://agentmods.dev/badge/skills/jeunessegamesee/clew/research-use-case.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 | $0.00051 | $0.00484 |
| Opus 5 | $0.00026 | $0.00242 |
| Sonnet 5 | $0.00010 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
research-use-case 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.
What it actually says
Research use-case flows
This is one turn of the coverage loop. Measure is the skill; research is the actuator. See loop.md.
Read research.md, monorepo.md, score.md, tree.md.
- Red —
clew loop --root <repo>. Ifreflected, stop (or one P1). Ifempty, cartograph one service. Ifincomplete, the printed next P0 is the only gap this turn.clew score --root <repo>shows drift (spec/CBM/OTLP with no tree). - Act — that neighborhood only (Input → Branches → Output). Smallest capture. Monorepo: update
docs/flows.mdedges. - Green —
clew loop --root <repo>again. Score or P0 count must move. If not, the write did not touch a scored hole — fix it before another gap. - Hold — commit. Next session starts at step 1. Do not remap the platform. CI:
clew score --fail-p0.
If this is a monorepo
Index hops (tree names + next only). Refresh docs/flows.md edges. The next P0 from the driver is the act target, not a survey of every service.
If this is one service
Same loop on that docs/hops.md.
Capture rules
- Trees: Input → Branches → Output. Event can be a tree (dispatch).
- One example JSON per path you actually saw.
- Cite contracts. If the span died, stitch + log line.
- Do not invent hops to look complete. Do not dump the monorepo into context.
Next session starts from the files you wrote. That is auto-research.
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 · 33 lines · 51 tokens per session scan A 15558425ee90
research-use-case is a skill published in the GitHub repository jeunessegamesee/clew (0 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 484 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".