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 feniix/pi-extensions --skill exa-research-plannergit clone --depth 1 https://github.com/feniix/pi-extensionsWrote 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/feniix/pi-extensions/exa-research-planner)<a href="https://agentmods.dev/skills/feniix/pi-extensions/exa-research-planner"><img src="https://agentmods.dev/badge/skills/feniix/pi-extensions/exa-research-planner/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/feniix/pi-extensions/exa-research-planner"><img src="https://agentmods.dev/badge/skills/feniix/pi-extensions/exa-research-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.03953 |
| Opus 5 | $0.00039 | $0.01976 |
| Sonnet 5 | $0.00016 | $0.00791 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
exa-research-planner 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 11d 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exa Research Planner
Use this skill to turn a vague or broad research request into a high-quality Exa research workflow, then optionally execute web_research_exa when the user clearly wants deep synthesis.
This skill has two jobs:
- Research planning — sharpen the question, decide whether cheap discovery is useful, track criteria/source/gap state with the local
exa_research_*planning tools, and draft a strong deep-research payload. - Explicit deep-research execution — when the user directly asks for deep research or approves a draft, run
web_research_exaand return a source-grounded synthesis.
Operating Modes
Choose the mode from the user's request.
| Mode | Use When | Behavior |
|---|---|---|
| Plan-only | User asks to design/refine a research prompt, scope a landscape, or reduce cost | Clarify, optionally do cheap discovery, draft a payload, and ask before execution. |
| Recon-first | Topic is broad, terminology is unclear, or trusted sources are unknown | Run cheap discovery with available search/fetch tools, then refine the deep-research spec. |
| Explicit deep-research execution | User says “do deep research,” “run deep research,” “deeply research,” or equivalent | Clarify only missing essentials, then run web_research_exa if available. A direct user request to run deep research counts as approval. |
Do not force an explicit deep-research request through a long planning loop. If the user has already asked to run deep research and the brief is usable, execute the deep research rather than asking for another confirmation.
Tool Availability Rules
Build the workflow only from tools actually available in the current session.
Local planning tools, enabled by default when no explicit enabledTools allowlist is configured and safe to use without an Exa API key:
exa_research_step— record one planning step with criteria, sources, gaps, assumptions, and next action.exa_research_status— inspect current planning state without mutating it.exa_research_summary— produce a human-readable brief, execution plan, source pack, or labeled optional payload.exa_research_reset— clear the active in-memory planning session.
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.
- 11d ago First seen · 402 lines · 79 tokens per session scan A faae8a9a1449
exa-research-planner is a skill published in the GitHub repository feniix/pi-extensions (23 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 3,953 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
qamap-pr-qa
Local zero-LLM PR QA workflow. Use when an agent is preparing, updating, finalizing, or reviewing a pull request, asks what the PR should test, or needs commit-backed change intent, affected behavior, QA scenarios, evidence, validation commands, optional automation drafts, and manifest repair guidance.
ts-debug
TypeScript/Node debugging expert. Use when the user needs to debug, profile, or trace TypeScript or Node.js code — e.g. "how do I debug this", "find the memory leak", "why is this slow", "add a breakpoint", "profile this function", "why won't the process exit".
typescript-conventions
Use when writing, reviewing, or refactoring TypeScript or JavaScript code — naming conventions, type annotations, private fields, null vs. undefined, async/await pitfalls, and module structure.
migrate-to-shoehorn
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
setup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
migrate-to-shoehorn
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.