gtm-pipeline
CLAUDE.md16 starsChanged 49 days agoApache-2.0View on GitHub
Read AGENTS.md (how the repo works, for any agent) and REVIEW.md (the quality bar). This file adds only what is specific to Claude Code. The fan-out stages run as workflows in .claude/workflows/. Each passes a narrow agent type from .claude/agents/ (web tools only, no skill listing), which keeps each sub-agent's starting context small. Pass agentType: '' in a workflow's args to fall back to the generic sub-agent. Every workflow returns failed[] (or unscored_ids); report those.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- activateSkill
- company-discoverySkill
- company-enricherSkill
- contact-qualifierSkill
- contact-sourcerSkill
- email-finderSkill
- gtm-setupSkill
- gtmSkill
- phone-finderSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Read AGENTS.md (how the repo works, for any agent) and REVIEW.md (the quality bar).
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
Read AGENTS.md (how the repo works, for any agent) and
REVIEW.md (the quality bar). This file adds only what is specific to Claude Code.
Commands
| Command | What it does |
/gtm-setup | First run: writes your ICP, personas, segments, exclusions and do-not-contact file from your website and a few answers, then checks your setup |
/gtm <brief> | Runs the pipeline from a plain-English brief |
/gtm status <list_id> | Shows what ran, what was skipped, cost, and open warnings (from the run ledger) |
/gtm resume <list_id> | Continues a list from its last completed stage with its frozen plan |
/company-discovery, /contact-sourcer, /contact-qualifier, /email-finder, /phone-finder, /activate | One stage on its own |
Workflows and agent types
The fan-out stages run as workflows in .claude/workflows/. Each passes a narrow agent type
from .claude/agents/ (web tools only, no skill listing), which keeps each sub-agent's
starting context small. Pass agentType: '' in a workflow's args to fall back to the generic
sub-agent. Every workflow returns failed[] (or unscored_ids); report those.
| Workflow | Agent type | Model |
discover-companies | company-researcher | Sonnet |
enrich-companies | company-intel-researcher | Haiku per dimension, Sonnet to synthesize |
preview-titles | people-sourcer | Sonnet |
source-people | people-sourcer | Sonnet |
score-leads | lead-scorer | Haiku |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

