Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mgallet92i/waterfall/plugin install 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/skills/mgallet92i/waterfall/wf-tl-light)<a href="https://agentmods.dev/skills/mgallet92i/waterfall/wf-tl-light"><img src="https://agentmods.dev/badge/skills/mgallet92i/waterfall/wf-tl-light/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mgallet92i/waterfall/wf-tl-light"><img src="https://agentmods.dev/badge/skills/mgallet92i/waterfall/wf-tl-light.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.01286 |
| Opus 5 | $0.00029 | $0.00643 |
| Sonnet 5 | $0.00012 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
wf-tl-light 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 10d 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.
wf-tl-light — TL solo-impl mode subagent-light
⚠ CONSTITUTION — Règles universelles Waterfall
Lire obligatoirement avant toute action :
agents/_shared/constitution.md
Rôle
TL-light est spawné deux fois par PM via Agent :
- Passe 1 : rédiger
design.md+tasks.md. Terminer l'appel après production detasks.md. - Passe 2 : implémenter toutes les tâches T-xxx de
tasks.mden solo.
Pas de sous-agent DV. TL implémente directement. (EX-008, TF-010) Pas de worktrees. Travail dans le répertoire principal. Micro-tweaks PM autorisés : PM peut corriger < 5 lignes sans logique métier sans respawn TL. (TF-018)
Session INV — Premier usage de wf-orchestrate.sh
Avant tout --query ou --complete, exécuter :
bash ${CLAUDE_PLUGIN_ROOT}/scripts/wf-orchestrate.sh --help
Passe 1 — Design + Tasks
Étape 1 — Lire specs.md en entier
# Lire le brief reçu de PM pour extraire le need_name et le work_dir
# Puis lire specs.md avant toute action (INV-BRIEF-DISCIPLINE)
Lire wf/needs/<name>/specs.md dans son intégralité avant de commencer.
Étape 2 — Rédiger design.md
Produire wf/needs/<name>/design.md compact :
- Architecture et composants touchés
- Choix techniques et ADR (Architecture Decision Records)
- Interfaces entre composants
- Data model si pertinent
- Risques identifiés
- Traçabilité EX-xxx → composant responsable
bash ${CLAUDE_PLUGIN_ROOT}/scripts/wf-orchestrate.sh <name> --complete TECHNICAL_DESIGN:GENERATE_DESIGN
Les steps REVIEW (agent=rv) sont auto-skippés.
Étape 3 — Rédiger tasks.md
Produire wf/needs/<name>/tasks.md au format T-xxx :
- Tableau principal : ID, exigences, description, fichiers, statut
- Détail par tâche : critères de fin, dépendances, effort
- Chemin critique
- Plan de parallélisation (même si solo, documenter l'ordre)
bash ${CLAUDE_PLUGIN_ROOT}/scripts/wf-orchestrate.sh <name> --complete PLANNING:GENERATE_TASKS
bash ${CLAUDE_PLUGIN_ROOT}/scripts/wf-orchestrate.sh <name> --complete PLANNING:ASSIGN_WORKTREES
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.
- 10d ago First seen · 135 lines · 58 tokens per session scan A 260c7a087ca3
wf-tl-light is a skill published in the GitHub repository mgallet92i/waterfall (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,286 once invoked, about $0.0003 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 skills, from other repositories
start
Use this skill when the user runs /start, says "start", "enable the SDLC workflow", "I want to build", "I want to fix", "set up", "get started", or otherwise signals they want to activate or re-enable the SDLC workflow. Handles three distinct paths based on marker state — fresh install (opt-in activation), re-enable…
domain-expert
Use this skill during /plan (between scope validation and writing the plan artifact) to inject domain-specific context, gap questions, and regulatory concerns into the plan. Triggers automatically when the plan skill evaluates the task and scope.md against the domain registry in domains/index.json using semantic…
plan
Use this skill at the START of every coding task — new builds, bug fixes, and change requests. Classifies the work item, validates it against project scope, produces a high-level estimate, proposes a technology stack, and checks stack compatibility. Writes a plan artifact to .claude/sdlc/plans/ that every downstream…
configure
Use this skill when the user runs /configure, /configure --needs, or /configure --check. Also auto-invoked by env-detect.sh on fresh install (Layer 0) and by skills that find required config missing at runtime (Layer 2). Guides setup of config/tools.json and config/tools.local.json through a question bank; handles…
status
Use this skill when the user asks "where am I", "what's the current task", "what's blocking me", "show status", "what needs sign-off", or "what's next". Prints a snapshot of the active plan, gate, sign-off progress, and next action. Reads only — writes nothing.
analyze
Use this skill after Phase 1 Plan to create or intake requirements for a task. Produces requirements with stable IDs (REQ-001, REQ-002, ...), validates each requirement against the project's scope statement, and — critically — halts and asks for UX designs and brand guidelines whenever the work touches a frontend or…