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 instructions/sourcey/startup-credits/agents-mdgit clone --depth 1 https://github.com/sourcey/startup-creditsWhat 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 | $0.00465 | $0.00465 |
| Opus 5 | $0.00233 | $0.00233 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
startup-credits AGENTS.md 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 2d 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.
What it actually says
Repository boundary
This is sourcey/startup-credits: the thin public YAML contribution
repository. “Startup Credits” is only this GitHub repository's name.
Allowed:
entities/**/*.yaml;- concise contributor, legal, and repository-boundary documentation; and
- minimal GitHub metadata and YAML workflows that invoke digest-pinned tools owned by the private Sourcey workspace.
Forbidden:
- executable code, packages, applications, scripts, CLIs, tests, fixtures, or build systems;
- contracts, schemas, OpenAPI/MCP generators, scanners, evidence operations, captures, trust material, authority objects, prompts, source inventories, or internal state;
- generated catalog or release snapshots, manual live selectors, compatibility layers, shims, duplicated definitions, or consumer-specific copies; and
- semantic-version changes,
v2shapes, or product/package naming decisions without Kam's explicit approval.
Pull-request CI processes only changed Entity files and their exact identity dependency closure. It must never rebuild the full catalog. Merge is the sole human activation and every live surface advances from the same resulting live head.
The public sourcey/validation status must start automatically for an opened or updated
data pull request, use the exact digest-pinned workspace-owned verifier, and
return actionable field errors before private review. sourcey/admission is a
separate Sourcey-owned evidence gate and never contributor-authored work.
Evidence review is semantic, not a verbatim-copy test. Published factual values need located source support; neutral Sourcey titles, summaries, descriptions, and taxonomy classifications may faithfully express cited facts in different words. Sourcey-owned IDs, encodings, and capture metadata are not claims that a vendor page must literally contain. The private Catalog policy and evaluator are the sole authority for that distinction; this repository does not restate or implement it.
entities/ is the only public data collection. Programs and Offers are nested
in their owning Entity document; repository evidence remains in that same
document but outside the shared entity envelope. Do not add a generic
data/ wrapper or another top-level collection unless Kam explicitly approves
a genuinely independent public authoring surface.
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.
- 2d ago First seen · 48 lines · 465 tokens per session scan A 0bf4817a27a5
startup-credits AGENTS.md is an instructions file published in the GitHub repository sourcey/startup-credits (140 stars, last pushed 3d ago), licensed MIT. It adds 465 tokens to every session, about $0.0023 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.