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/wardmos/waybill/agents-mdgit clone --depth 1 https://github.com/wardmos/waybillWhat 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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
waybill 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Waybill creates portable, local-first handoff bundles for moving unfinished agent work between coding agents.
- Keep specs, examples, adapters, and generated text portable across agent CLIs.
- Keep canonical shared resources only under
skills/. Keep agent-specific wrappers only underadapters/, plus the repository-root Codex manifest and.agents/plugins/marketplace.json, in git. Standalone adapter bundles and agent-local installations are generated outputs. - Keep common dispatch and operation behavior under
skills/. Limit adapter wrappers to platform metadata, exact agent identity, argument bridging, and platform-specific resource paths. - Do not commit local artifacts such as handoff bundles, package installs, caches, bytecode, archives, or generated reports.
- Keep changes small, focused, and consistent with existing module boundaries.
- Do not add dependencies unless clearly justified; prefer the Python standard library.
Privacy
- Do not commit secrets, tokens, API keys, cookies, private user data, personal emails, local machine paths, real handoff bundles, archives, logs, screenshots, or private planning notes.
- Keep examples and tests synthetic.
- Do not weaken privacy, redaction, bundle validation, packing, or unpacking safeguards without focused tests.
- Do not add release tags or release wording until an actual release is being prepared.
Checks
- Run
python3 scripts/validate-waybill.pyafter code, adapter, spec, example, or docs changes. - For Python changes, also run
python3 -m py_compile cli/waybill waybill_core/*.py scripts/validate-waybill.py. - Add or update validation coverage for behavior changes, bug fixes, and privacy-sensitive paths. If a check cannot run locally, document why.
- Use
scripts/smoke-agents.sh --dry-runfor smoke command generation. Only run real agent smoke tests when explicitly asked. python3 scripts/validate-waybill.pybuilds standalone adapters in a disposable directory. Usescripts/build-adapters.pyonly when a local self-contained distribution is needed; do not commit its output.- There is no separate adapter synchronization step. Edit shared resources in
skills/, edit only agent-specific wrappers inadapters/, and let the repository validator compare every generated distribution target.
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 · 62 lines · 630 tokens per session scan A ccae2df019cd
waybill AGENTS.md is an instructions file published in the GitHub repository wardmos/waybill (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 630 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 2026-08-31.
Other instructions, from other repositories
meta-llm-charter CLAUDE.md
Instructions for entropyvortex/meta-llm-charter, covering meta v3.1 core charter, bias, meta-0, r1 decompose and r2 ask gate.
awesome-reviewers CLAUDE.md
Instructions for baz-scm/awesome-reviewers, covering awesome reviewers — repository guidelines, what this project is, source of truth, site layer and machine interface.
code-context AGENTS.md
Instructions for infino-ai/code-context, covering code-context: notes for ai agents, project overview, repo map, build, test, gates and conventions.
gtm-cheat-codes CLAUDE.md
Instructions for zapier/gtm-cheat-codes, covering repo conventions and commits.
Stata-CLI AGENTS.md
Instructions for Utolaris/Stata-CLI, covering agents.md, project structure and working rules.
agent-workspace AGENTS.md
Instructions for VietHann/agent-workspace, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.