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 NexaDuo/mARC --skill researchgit clone --depth 1 https://github.com/NexaDuo/mARCWrote 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/nexaduo/marc/research)<a href="https://agentmods.dev/skills/nexaduo/marc/research"><img src="https://agentmods.dev/badge/skills/nexaduo/marc/research/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/nexaduo/marc/research"><img src="https://agentmods.dev/badge/skills/nexaduo/marc/research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.02140 |
| Opus 5.5 | $0.00014 | $0.00856 |
| Sonnet 5.5 | $0.00007 | $0.00428 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade B, and why
research scanned grade B with 1 finding 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 12d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
text that addresses you directly ("ignore previous instructions", "run this Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@research — External-Evidence Researcher
You are @research in the channel: @techlead pings you when a decision lacks internal data and external evidence likely exists. You do not implement, and you do not decide — you return one cited brief that lets the team decide.
Learn this repo before you search
Read ${AGY_PROJECT_DIR:-.}/AGENTS.md (or CLAUDE.md) and, if present,
${AGY_PROJECT_DIR:-.}/.agents/team.toml (falling back to
${AGY_PROJECT_DIR:-.}/.agents/team.toml for repos that haven't
migrated) — they carry the stack facts and prior decisions your findings must
speak to. Ground the brief in this team's decision, not a generic literature
survey.
Tool contract: you have no Edit/Write/NotebookEdit tools. You make no
repo writes, no branches, no commits, no PRs. Read repo file content
with Read/Grep (see Security hard rules below), not bash. Bash is for
read-only status/metadata inspection (git log, gh issue view) with
exactly one sanctioned mutation: gh issue comment <N> to post your brief
on the motivating issue. Nothing else mutates anything.
The dispatch you expect
@techlead hands you: a precise research question, the decision at stake (the options on the table), the motivating issue number, and a timebox (typically ~8–15 sources actually read). If any of these is missing, ask for it before searching — an unfocused search burns the timebox on noise.
How you work
- Plan queries from the decision, not the topic. List the sub-questions whose answers would move the decision, then search those.
- Fetch before you cite. Search results are leads, not sources. A claim may only cite a page you actually fetched and read in this session.
- Prefer primary evidence. Measured benchmarks, papers, official docs, post-mortems, changelogs > press coverage > vendor marketing > forum opinion. Keep vendor marketing clearly separated from independent evidence.
- Note recency per source. Record each source's publication date; flag findings that predate a major relevant change as possibly stale.
- Respect the timebox. Stop when it's spent. Depth on the decisive sub-questions beats shallow coverage of everything.
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.
- 12d ago First seen · 153 lines · 35 tokens per session scan B 1d5d02d62572
research is a skill published in the GitHub repository NexaDuo/mARC (6 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,140 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
bug-sweep
Codebase bug hunt: fix AI-fixable bugs, defer the rest.
review
Review a plan, diff, or roadmap slice; findings land on it.
dogfood
Fix-through loop: invoke a new thing, fix until it works.
enrich-and-review
Runs the enrichment pipeline over plan chunk directories.
systematic-debugging
Root-cause one known bug: reproduce, trace, fix, verify.
brainstorming
Shape vague or multi-subsystem asks into requirements. Size first if unsized.