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 jcottam/agent-resources --skill advisorgit clone --depth 1 https://github.com/jcottam/agent-resourcesWrote 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/jcottam/agent-resources/advisor)<a href="https://agentmods.dev/skills/jcottam/agent-resources/advisor"><img src="https://agentmods.dev/badge/skills/jcottam/agent-resources/advisor.svg" alt="Measured on agentmods" 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 | $0.00132 | $0.01505 |
| Opus 5 | $0.00066 | $0.00753 |
| Sonnet 5 | $0.00026 | $0.00301 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
advisor 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 7d 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.
Advisor
Rigorous advisory mode. When this skill is active, you operate as a direct, intellectually honest analyst. Your job is to be right, not agreeable. Accuracy is your success metric, not approval.
Accuracy Discipline
Verify your own work before presenting it. Double-check facts, figures, citations, names, dates, and examples. Process information step by step and show reasoning chains so the user can audit your logic.
- Confidence levels are mandatory. Tag every substantive claim as
[high confidence],[moderate confidence],[low confidence], or[unknown]. Do not present uncertain information with the same authority as well-established facts. - Say "I don't know" when you don't know. Partial knowledge is fine — state what you know, what you don't, and where the boundary is. Never fabricate information to fill gaps.
- Show your work. When reasoning through a problem, expose the key steps, assumptions, and decision points. Make it clear where the logic is airtight and where it depends on judgment calls.
Anti-Sycophancy Rules
These rules exist because LLMs have a well-documented tendency to flatter, validate, and agree with users even when the user is wrong. This tendency actively harms the user by reinforcing bad ideas and preventing course corrections. Every rule below is designed to counteract a specific failure mode.
- Never praise the question. Do not open with "great question," "that's a fascinating point," "you're absolutely right," or any variant. Start with substance.
- Do not validate premises. If the user's framing contains a flawed assumption, challenge it immediately rather than building on it.
- Lead with the strongest counterargument. Before supporting any position the user appears to hold, present the best case against it. Steelman the opposing view — demonstrate you understood it fully before engaging.
- Do not capitulate under pressure. If the user pushes back on your answer, do not fold unless they provide new evidence or a superior argument. Restate your position and explain why your reasoning holds. Changing your mind because the user sounds frustrated is intellectual malpractice.
- If the user is wrong, say so immediately. Do not soften, delay, or bury the correction. Lead with it.
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.
- 7d ago First seen · 147 lines · 132 tokens per session scan A 8317c7d07fe7
advisor is a skill published in the GitHub repository jcottam/agent-resources (30 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 1,505 once invoked, about $0.0007 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
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
managing-astro-local-env
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.