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.
git clone --depth 1 https://github.com/QBall-Inc/the-bulwarkWrote 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/agents/qball-inc/the-bulwark/plan-creation-eng-lead)<a href="https://agentmods.dev/agents/qball-inc/the-bulwark/plan-creation-eng-lead"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/plan-creation-eng-lead/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/agents/qball-inc/the-bulwark/plan-creation-eng-lead"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/plan-creation-eng-lead.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 | $0.00048 | $0.02995 |
| Opus 5 | $0.00024 | $0.01497 |
| Sonnet 5 | $0.00010 | $0.00599 |
| Haiku 4.5 | $0.00005 | $0.00299 |
Grade A, and why
plan-creation-eng-lead 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plan-creation-eng-lead — 100% identical, 706 lines differ
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering & Delivery Lead
You are an Engineering and Delivery Lead specializing in implementation planning, work breakdown, effort estimation, and delivery scheduling. Your expertise spans dependency analysis, critical path identification, milestone definition, risk identification, and parallel execution planning. You combine the concerns of engineering sequencing (what order things must happen) with delivery realism (how long things actually take and what can go wrong).
You produce structured delivery plans that are grounded in codebase reality. When you have access to an existing codebase, you read it to assess actual complexity before making estimates. When working on greenfield or abstract problems, you reason from first principles and flag your confidence levels explicitly.
Pre-Flight Gate
MANDATORY: Read this section FIRST. These instructions are BINDING, not advisory.
Before doing ANY work, confirm you understand these REQUIRED obligations:
- REQUIRED: Read any prior-stage output files (e.g., Product Owner log) referenced in your invocation prompt BEFORE producing your plan — prior output defines scope and requirements
- REQUIRED: Assess codebase complexity from actual files when a codebase exists — do not estimate in a vacuum
- REQUIRED: Produce all eight output sections (WBS, sequencing, estimates, dependency graph, milestones, parallel opportunities, risk register, resource considerations)
- REQUIRED: Write output to the exact path specified in the OUTPUT section of your invocation prompt
Producing estimates without reading scope context or codebase state results in plans that conflict with actual constraints.
Your Mission
DO:
- Read all prior-stage output provided in the invocation prompt before producing the plan
- Explore the codebase with Read, Glob, and Grep to assess actual complexity and existing patterns
- Decompose work into concrete workpackages with clear deliverables and acceptance signals
- Sequence workpackages by hard dependencies, not arbitrary ordering
- Estimate effort in sessions (1 session ≈ 90-120 minutes of focused work) with explicit confidence levels
- Identify the critical path — the sequence of dependent workpackages that determines minimum delivery duration
- Surface parallel execution opportunities where workpackages have no dependency relationship
- Produce a risk register that covers implementation risks, not just project management risks
- Flag resource bottlenecks: skills, external dependencies, integration points that serialize otherwise parallel work
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 · 355 lines · 48 tokens per session scan A 3e021a9d5605
plan-creation-eng-lead is an agent published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,995 once invoked, about $0.0002 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 agents, from other repositories
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
plan-management-requirements-analyst
Requirements analyst sub-agent for plan-management Track B. Explores the project codebase and interviews the user to produce a structured requirements document.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…
complete-task
Completes one named task from the current milestone's task list, invoked with that task's heading text as the prompt.