Borrowing it
Nothing to install: this file belongs to chrisgleissner/llm-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrisgleissner/llm-tools/main/.github/prompts/plan-driven-implementation.prompt.mdgit clone --depth 1 https://github.com/chrisgleissner/llm-toolsWrote 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/commands/chrisgleissner/llm-tools/plan-driven-implementation)<a href="https://agentmods.dev/commands/chrisgleissner/llm-tools/plan-driven-implementation"><img src="https://agentmods.dev/badge/commands/chrisgleissner/llm-tools/plan-driven-implementation/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/commands/chrisgleissner/llm-tools/plan-driven-implementation"><img src="https://agentmods.dev/badge/commands/chrisgleissner/llm-tools/plan-driven-implementation.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 | $0.00010 | $0.01167 |
| Opus 5.5 | $0.00004 | $0.00467 |
| Sonnet 5.5 | $0.00002 | $0.00233 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
plan-driven-implementation 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 26d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-Driven Implementation
Deliver a complete, production-ready implementation using a plan-first, execution-driven workflow.
This is an execution prompt, not an analysis prompt.
Do not stop after planning. Do not stop after partial implementation. Carry the work through to full completion unless genuinely blocked by an external constraint.
Core Objective
You must:
- Extend the existing execution plan (PLANS.md)
- Continue implementation from the current state
- Execute all remaining tasks to completion
- Ensure:
- all tests pass
- coverage ≥ 91%
- no partial or placeholder logic remains
Non-Negotiable Rules
- This is an EXECUTION task
- You must act as a deterministic execution engine, not a planner
- You must not stall, summarize, or defer work
- You must not leave tasks partially complete
- You must not overwrite existing valid plans
- You must not stop until convergence criteria are satisfied
Phase 1 — Plan Reconciliation and Extension
You must treat PLANS.md as the authoritative execution plan.
If PLANS.md exists:
You MUST:
- Read the entire file
- Identify:
- completed tasks
- in-progress tasks
- remaining tasks
- gaps or missing work
- Validate whether the plan is still correct
Then:
- DO NOT rewrite or delete existing content
- ADD a new section at the end:
Plan Extension —
This section must include:
- newly identified tasks
- corrections to previous assumptions
- missing validation steps
- any reordered or refined tasks (with justification)
If earlier tasks are incorrect, mark them clearly as:
- SUPERSEDED
- or UPDATED (with explanation)
If PLANS.md does NOT exist:
Create it using the full plan structure:
- task breakdown
- ordering
- dependencies
- validation per task
- DONE criteria
- coverage strategy
After updating PLANS.md: YOU MUST IMMEDIATELY START IMPLEMENTATION
Phase 2 — Execution Loop
You must execute tasks ONE AT A TIME.
Tasks must be selected in this priority order:
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.
- 26d ago First seen · 304 lines · 10 tokens per session scan A 2d3d19e0bebf
plan-driven-implementation is a command published in the GitHub repository chrisgleissner/llm-tools (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 1,167 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-03.
Other commands, from other repositories
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
octo-deliver
Delivery phase - Review, validate, and test with multi-AI quality assurance.
api-aqa-flow
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
ui-aqa-flow-code-analysis
Phase 3 Code Analysis of ui-aqa-flow.