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 alexmond/alexmskills --skill research-sweepgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/research-sweep)<a href="https://agentmods.dev/skills/alexmond/alexmskills/research-sweep"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/research-sweep/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/alexmond/alexmskills/research-sweep"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/research-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 41 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 258 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00125 | $0.05471 |
| Opus 5 | $0.00063 | $0.02736 |
| Sonnet 5 | $0.00025 | $0.01094 |
| Haiku 4.5 | $0.00013 | $0.00547 |
Grade A, and why
research-sweep 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 10d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel research sweep
Try it:
/research-sweep:research-sweep every open-source vector database— or say "give me an exhaustive catalog of public datasets for X".
This is the discover orchestrator — one of three that run on the same shared role substrate. Where dev-crew delivers a gated artifact (roles related by handoff) and brainstorm-panel decides a judgment (roles related by disagreement), the sweep discovers verified, cited findings: it composes a task-fit team of coverage roles for an information space, fans them out so each owns a disjoint angle (roles related by independence — no clash, no overlap), dedups, and adversarially verifies. The three chain — research discovers the facts, panel decides what to do, crew delivers it — and they share roles: the same skeptic is a panel seat, a crew adversarial check, and this skill's fact-verifier. (See the Role System architecture for how that shared substrate works across all three.)
For when the user wants coverage that is exhaustive, not representative. Compose the coverage roles, launch them as N parallel research agents with disjoint scopes and identical contracts, assemble their YAML/JSON outputs into one file via shell redirect — never letting the agent transcripts pass through the main context — then run an adversarial verification pass before trusting the result.
The methodology has two halves: fan-out (parallel coverage roles on disjoint slices) and verification (adversarial review of what came back). Skipping the second half produces a large but unreliable dataset.
Scope check — sweep, or a single agent?
The trigger phrases live in the description; what needs judgment once loaded is whether the ask is big enough to justify a fan-out.
Borderline asks (one agent may suffice — decide before composing a team):
- "a list of …" with no quantity hint
- "research X" — could be a single Explore agent
Hand the task back to a single agent if:
- The user wants 5–20 items (single Explore or general-purpose agent is enough)
- The domain is narrow enough that one agent can cover it well
- The data already exists in the repo and just needs querying
What ships with it
1 file 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.
- 10d ago First seen · 276 lines · 125 tokens per session scan A 91ecd51d2389
research-sweep is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 5,471 once invoked, about $0.0006 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
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.