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.
git clone --depth 1 https://github.com/thangnguyenworkspace/company-research-pipelineWrote 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/commands/thangnguyenworkspace/company-research-pipeline/research-topic)<a href="https://agentmods.dev/commands/thangnguyenworkspace/company-research-pipeline/research-topic"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/research-topic/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/commands/thangnguyenworkspace/company-research-pipeline/research-topic"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/research-topic.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 | $0.00026 | $0.01230 |
| Opus 5 | $0.00013 | $0.00615 |
| Sonnet 5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
research-topic scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Triage: list the claims that are load-bearing AND (single-source, old, of unknown origin, or time-sensitive). Fan out verification agents over that list, framed adversarially ("your job is to refute this claim"), targeti How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Topic
Build one dossier for: $ARGUMENTS (a company slug and a topic). If either is missing, ask. The company folder research/{slug}/ must exist (run /research-company first if not). The topic's question, ownership boundary, and analytical spine are defined in method/03-topics.md; the full method is method/01-pipeline.md section 2.
Step 1: Load
Read in full: 00-scope.md, 00-coverage-map.md, every already-written dossier-*.md for this company, and this topic's inbound-queue/pending/ entries. Then draft the dossier's section plan: the numbered sections, each defined by the question it answers (scaffolding, never conclusions). Present the section plan plus the sub-question carve for the gather, and pause for approval.
Step 2: Gather
Fan out 2 to 4 parallel research agents, each owning a disjoint sub-question slice. When the topic's evidence lives on LinkedIn or X, include a slice that runs the /social-crawl motion; when the company has public repos and the topic is product, include a /repo-recon slice. Dedicate one slice (or one agent) to the skeptic pass: hunting evidence against the scope's stated prior.
Every gather agent prompt must include:
- The slice: sub-questions covered, sub-questions explicitly excluded.
- The loop: up to 3 reason-search-reflect rounds; at most 2 Exa searches plus 1 batched crawl per round; stop on the named-gap test, diminishing returns, or the round cap.
- The grading rules: two-axis
[R·C]per source, sole-source caps at C3 (method/02-epistemics.mdsection 3). - The tool rules:
method/04-tools.md(crawlmaxCharacters, explicitnumResults, natural-language queries, pre-score from result text before crawling, live-fetch systems of record for time-sensitive facts). - Organize-only: report sourced findings, never conclusions or tags. Every finding carries its external source URL.
- Output: one file per agent at
research/{slug}/{topic}/01-gather/gather-{slice}.mdpertemplates/gather-report.md. - Read files past truncation.
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 · 64 lines · 0 tokens per session scan A be500c94d907
research-topic is a command published in the GitHub repository thangnguyenworkspace/company-research-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,230 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-actor
Guided Apify Actor development with best practices and systematic workflow.
status
Show current research session state and progress.
resume
Resume a previous research session from progress file.
init
Manually initialize or reload research context for sigint.
augment
Deep-dive into a specific area of current research.
issues
Create GitHub issues from research findings as atomic deliverables.