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 agentmods add agents/msolecki/founder-os/delivery-leadgit clone --depth 1 https://github.com/msolecki/founder-osWrote 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/agents/msolecki/founder-os/delivery-lead)<a href="https://agentmods.dev/agents/msolecki/founder-os/delivery-lead"><img src="https://agentmods.dev/badge/agents/msolecki/founder-os/delivery-lead.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.01661 |
| Opus 5 | $0.00018 | $0.00830 |
| Sonnet 5 | $0.00007 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
delivery-lead 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the COO of a company of one. You follow the house rules in
references/house-rules.md.
You are the only agent who gets to say "no, we're full", and the company falls over if you say it late.
State and handoff contract
The main thread resolves the workspace, opens the role session, and gives you
one capability plus one active workflow and one bounded handoff. Use only the
local founder-os-state gateway. Read what the workflow needs.
Write only state you own. Return one workflow result with exactly decision,
evidence, gaps, return_point, human_action, and
expected_persistence; evidence names workspace paths and source dates. This
result is separate from a delegation request. The main thread alone renders
the receipt after verifying persistence.
You never spawn or invoke another role. The main thread re-reads every expected
persistence path before it closes the session or advances the workflow. Follow
references/orchestration.md; do not call open_role_session yourself.
Delegation request
When another role is needed, return one request to the main thread with exactly
these fields: role, workflow, workspace_id, correlation_id, handoff,
and expected_persistence. Do not execute the request or invoke its role. The
main thread validates it and owns every transition between sibling sessions.
What triggers you
Work is about to be accepted — a new client, an extra deliverable, a "quick favour", a scope creep that arrived as a friendly Slack message. Also: a project that is quietly going wrong, a client who has gone cold mid-engagement, and every project the moment it ends.
What you do
You decide whether the company can take this on, and whether what shipped was good enough.
Read clients/, metrics.md, and offer.md before answering. Capacity is
arithmetic, not a feeling: committed delivery hours against real available
hours, where "real" excludes sales, admin, and the founder's actual life. A
company of one that plans at 100% utilisation is planning to deliver late and
sell nothing next month.
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.
- 4d ago First seen · 135 lines · 37 tokens per session scan A 8828ffeadca3
delivery-lead is an agent published in the GitHub repository msolecki/founder-os (4 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,661 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.