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/generous-corp/pulp/agents-mdgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/instructions/generous-corp/pulp/agents-md)<a href="https://agentmods.dev/instructions/generous-corp/pulp/agents-md"><img src="https://agentmods.dev/badge/instructions/generous-corp/pulp/agents-md.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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
pulp 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 today.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read CLAUDE.md before making any changes.
Before changing files, run tools/scripts/worktree_lineage.sh show --path ..
If the worktree is superseded, merged, or archived, follow its recorded
successor/disposition instead of resuming it. If no status is recorded,
classify the worktree before editing.
Decisions contract (read before touching fleet/CI config)
Settled build-system, CI, and release-automation decisions are recorded in
.agents/contract.toml — a schema-versioned, layered
(generic default layer + pulp overlay), agent-neutral file. Each decision
was bought with an incident; several were re-proposed by past agents and cost a
planning cycle each. Before proposing or writing a change to CI/fleet config
(the merge queue, Namespace/paid runners, auto-rebase or --adopt-head,
bump-at-merge, ccache depend-mode, squash auto-merge, static runner names, the
Debug macOS lane, warm build dirs), read the relevant rows:
python3 tools/scripts/decisions_contract.py --mode list # all rows
python3 tools/scripts/decisions_contract.py --mode surface --base origin/main # rows your diff touches
python3 tools/scripts/decisions_contract.py --mode validate # schema-check the file
Reversing a decision requires first proving its motivating incident class can no
longer occur (Step Zero). The read surface and the SessionStart/PostToolUse
hooks (hooks/scripts/decisions-contract-*.sh, wired for both Codex via
.codex/hooks.json and Claude via the plugin) are advisory context only — the
authoritative block is this CLI's validate gate plus CI required checks.
Vellum source-authority routing
.github/vellum-ownership.json is the authoritative source-routing projection.
For slices whose state is framework-authoritative-transferred, new generic
framework/rendering/UI work originates in Generous-Corp/vellum; Pulp changes
are limited to explicitly Pulp-owned integration, adaptation, or compatibility
work and must carry the required immutable change-event declaration.
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.
- today First seen · 47 lines · 633 tokens per session scan A 4a7639ebbe64
pulp AGENTS.md is an instructions file published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 633 tokens to every session, about $0.0032 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 2026-09-04.
Other instructions, from other repositories
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.