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 agentmods add skills/orin-dx/agent-plugins/researchnpx skills add orin-dx/agent-plugins --skill researchgit clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote 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/orin-dx/agent-plugins/research)<a href="https://agentmods.dev/skills/orin-dx/agent-plugins/research"><img src="https://agentmods.dev/badge/skills/orin-dx/agent-plugins/research.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 | $0.00170 | $0.00692 |
| Opus 5 | $0.00085 | $0.00346 |
| Sonnet 5 | $0.00034 | $0.00138 |
| Haiku 4.5 | $0.00017 | $0.00069 |
Grade A, and why
research 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 3d 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
Vanguard Research Skill
One skill, one pipeline — not a menu of separately-invokable modes. recon maps sources (internal specs/docs/code, dependency manifests, external references), reader reads only what the map points at, synthesizer resolves the findings into one report, risk-assessor reviews the resulting approach. The pipeline narrows itself to what's asked: a question answerable from internal sources alone gets scope: internal from recon and never touches external search; a request for risk review of an already-decided approach can hand risk-assessor that approach directly.
<language_agnostic_note> Recon detects the workspace language from manifest files present (Cargo.toml → Rust, package.json → Node/TypeScript, pyproject.toml → Python, etc.), then loads the appropriate shared/references search heuristics for that ecosystem. The skill is not language-specific. </language_agnostic_note>
<subagent_dispatch_matrix>
| Agent | Role | Model / Effort | Delegate When |
|---|---|---|---|
| recon | Source mapper | haiku / low | Start every research task here. Maps internal sources, external keywords, and existing implementations. |
| reader | Evidence extractor | sonnet / medium | Given the source map, reads each source and extracts findings with citations and confidence levels. |
| synthesizer | Recommendation producer | sonnet / medium | Given findings, synthesizes a research-report@1 with a falsifiable recommendation and confidence level. |
| risk-assessor | Risk prioritizer | sonnet / medium | Given a proposed approach or research-report@1, identifies and prioritizes technical risks with mitigations. |
</subagent_dispatch_matrix>
The recommendation is falsifiable: a spec or plan written from it will not be surprised by implementation reality.
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.
- 3d ago First seen · 45 lines · 170 tokens per session scan A 73aa3196acff
research is a skill published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed today), licensed MIT. It adds 170 tokens to every session and 692 once invoked, about $0.0009 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
campus-assignment-cleaner
Activates when a student or campus developer needs to make a working-but-messy codebase submission-ready before uploading it for grading. Trigger phrasings include "clean up my assignment before submitting", "remove debug prints and commented code", "tidy this up before I upload it to Moodle/Canvas/GitHub Classroom"…
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
agent-orchestration-multi-agent-optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
adhx
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.