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-company)<a href="https://agentmods.dev/commands/thangnguyenworkspace/company-research-pipeline/research-company"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/research-company/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-company"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/research-company.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 | $0.00023 | $0.00843 |
| Opus 5 | $0.00012 | $0.00421 |
| Sonnet 5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
research-company 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 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.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Company
Run the full pipeline from method/01-pipeline.md for the company: $ARGUMENTS
If no company name was given, ask for one before doing anything else.
Step 1: Resolve state
- Derive the working slug (kebab-case of the company name) and check whether
research/{slug}/already exists. - If it exists, read
research/{slug}/00-progress.mdand00-coverage-map.md, report where the engagement stands (which dossiers are done, what is queued), and resume from the next undone phase below. Do not redo completed work. - If it is new, continue to Step 2.
Step 2: Scope (Phase 0)
Interview the user briefly (3 questions maximum):
- Why this company, and what decision does the research feed?
- What is your current prior about the company? (Stated plainly; it will be tested, not protected.)
- Any known constraints: deadline, topics that matter most, sources to avoid?
Then scaffold the working folder:
research/{slug}/
├── 00-scope.md the answers above, written down
├── 00-progress.md one line per session/event; backflow log table
├── 00-coverage-map.md from templates/coverage-map.md
└── {topic}/ created lazily, one folder per topic as each starts
├── 01-gather/
├── 02-verification/
└── inbound-queue/{pending,archive}/
Step 3: Recon (Phase 1)
Run the recon pass per method/01-pipeline.md Phase 1:
- Broad Exa discovery across the company name, products, founders, funding, press. Natural-language queries; follow
method/04-tools.mdfor parameters. - Crawl the obvious primary surfaces (site, docs, blog, careers, funding databases, GitHub org) via the
/exa-crawlmotion. - Record name collisions the moment you notice them.
- Write
00-recon.md(provisional, labeled as such) and seed00-coverage-map.md.
Pause and present the recon summary plus the proposed topic order before continuing.
Step 4: Topic dossiers (Phase 2)
Walk the seven topics in order (thesis, company, product, buyers, competitive, activity, people; rationale in method/03-topics.md), one per 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.
- 12d ago First seen · 71 lines · 23 tokens per session scan A bd1e2b4e2b2c
research-company is a command published in the GitHub repository thangnguyenworkspace/company-research-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 843 once invoked, about $0.0001 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 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.