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/mgallet92i/waterfall/agents-mdgit clone --depth 1 https://github.com/mgallet92i/waterfallWrote 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/mgallet92i/waterfall/agents-md)<a href="https://agentmods.dev/instructions/mgallet92i/waterfall/agents-md"><img src="https://agentmods.dev/badge/instructions/mgallet92i/waterfall/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 | $0.03162 | $0.03162 |
| Opus 5 | $0.01581 | $0.01581 |
| Sonnet 5 | $0.00632 | $0.00632 |
| Haiku 4.5 | $0.00316 | $0.00316 |
Grade A, and why
waterfall 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 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — développer le framework waterfall
Guide de l'agent qui modifie ce repo (le framework lui-même). Trois publics, trois docs :
utilisateur → README.md ; agents d'un workflow en run → agents/_shared/constitution.md ;
dev du framework → ce fichier.
Philosophie
- La state machine est la seule source de vérité.
scripts/wf-orchestrate.shdécide ; les agents exécutent. Tout ce qui peut être décidé par le script doit l'être par le script, jamais délégué au jugement LLM (cause racine ARCH-03). - Personas hint-driven. Les
.mdne recopient JAMAIS les tables du script (step→agent, params, séquences) : le contrat runtime vient de--query(agent,hint,expected_params) et de--help. Toute table recopiée finit par mentir (ARCH-06) —tests/wf-doc-drift.batsl'interdit en CI. - Échec bruyant > défaut silencieux. Jamais de fallback muet vers un état par défaut (F-030 : état fantôme = pire mode de panne).
- Politique de retrait. Le rodage in vivo ajoute de la prose ; la dette de prose sature les contextes (ARCH-07). Chaque fix doit envisager une suppression, pas seulement un ajout.
- Noms canoniques d'artefacts :
PRD.md, specs.md, acceptance.md, design.md, tasks.md, tracking.md, review.md, ui.md, retro.md. Owners : constitution §Mapping artefacts → owners. Tout autre nom est un drift (F-033/F-034).
Carte du repo
scripts/wf-orchestrate.sh— state machine (~3600 l., bash + node/jq inline).--help= contrat complet (phases/steps générés depuisSTEPS[]).scripts/wf-step-agents.sh— tables step→agent + overrides light/dark (qui possède quel step).hooks/wf-auth.sh— hook PreToolUse : identité sur--complete(regex command-line) + matrice artefact→writers sur Write/Edit (file_path structuré, tous rôles) + flat-deny des écritures Bash d'artefacts (ARCH-08, zéro exception — canaux scriptés :--log,--append). Litagent_typedu payload harness ;.team-registry.json= traçabilité pure, jamais consulté pour l'auth (DEC-001).scripts/lib/wf-paths.sh— resolveurPROJECT_ROOTcanonique, sourcé par orchestrate/watchdog/registry (F-032). Ne jamais résoudre viascript_dir/...scripts/wf-watchdog.sh,wf-registry.sh,wf-read-config.sh(validation.wf-config.json),wf-check-*.sh(preflights).agents/*.md— personas des 8 rôles ;agents/_shared/constitution.md— invariants universels.commands/+skills/—/waterfall:new|resume|quit, variantes light (wf-pm-light,wf-tl-light).wf/templates/{fr,en}/— templates d'artefacts (miroirs) ;wf/needs/— runtime ;wf/archives/— needs clos (ne pas éditer).backlog.md— findingsF-xxx+ causes racinesARCH-01..10. À lire avant de toucher au cœur ; c'est l'historique des pièges déjà payés.tests/— bats : wf-auth (63), state machine (wf-orchestrate-*.bats, helper isoléwf-orchestrate-helper.bash), anti-drift doc (wf-doc-drift.bats).
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 · 171 lines · 3,162 tokens per session scan A dce865454781
waterfall AGENTS.md is an instructions file published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 3,162 tokens to every session, about $0.0158 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
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.
claude-account-switch AGENTS.md
AGENTS.md instructions for LightZirconite/claude-account-switch, covering claude + codex account switch - agent guide, product invariants, authentication ux, switching safety and provider parity and deliberate differences.
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).