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 rjmurillo/ai-agents --skill panning-for-goldgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/panning-for-gold)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/panning-for-gold"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/panning-for-gold/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/rjmurillo/ai-agents/panning-for-gold"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/panning-for-gold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Prompt Injection · line 12 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00093 | $0.02102 |
| Opus 5.5 | $0.00037 | $0.00841 |
| Sonnet 5.5 | $0.00019 | $0.00420 |
| Haiku 4.5 | $0.00009 | $0.00210 |
Grade A, and why
panning-for-gold 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 17d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Panning for Gold
Turn raw, unstructured capture into an evaluated, actionable inventory of threads. Four phases: Front-gate, Extract, Evaluate, Synthesize.
Triggers
| Trigger Phrase | Operation |
|---|---|
pan for gold |
Run the full extract -> evaluate -> synthesize procedure |
triage transcript |
Build inventory of threads from a raw transcript |
synthesize gold-found |
Generate the final gold-found file from evaluations |
When to Use
Use this skill when:
- You have a voice transcript, stream-of-consciousness note, or brain dump that contains many ideas mixed with noise.
- You need a deterministic procedure to triage which ideas merit deeper analysis.
- You want a permanent, structured artifact that the analyst agent or the spec-generator skill can consume.
Use a different skill when:
- The input is already structured (specs, ADRs, code). Use the analyst agent or the spec-generator skill instead.
- You only need a one-off summary. Use a generic summarizer.
Workspace Layout
The skill operates inside a workspace root. The default is ./.panning/ in the current working directory; override via --workspace <path> or the PANNING_WORKSPACE environment variable.
<workspace>/
|-- transcripts/ # Raw input (read-only after capture)
|-- inventories/ # Pass1 + final inventories
|-- evaluations/ # Per-thread evaluation files
`-- gold-found/ # Synthesized gold-found files
The script creates missing subdirectories on demand. It never overwrites an existing file unless --force is passed.
What ships with it
6 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.
- 17d ago Changed 095858233474
- 1mo ago Changed · +6 lines 5394436276c0
- 1mo ago Changed ce3acf876728
- 1mo ago First seen · 141 lines · 93 tokens per session scan A 1f40dc18c6cd
panning-for-gold is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,102 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
reuse-before-you-write
Use before writing any new function, helper, component or module - find what the repository, the standard library and the installed dependencies already provide, and use an established library instead of hand-rolled code for a non-trivial problem.
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
review-remote
Review open PR/MR and publish findings.
cowork-session
Claude Cowork shared AI pairing sessions with real-time sync, turn-taking, and collaboration context propagation.
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…