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/Fmarzochi/EGCWrote 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/fmarzochi/egc/prp-implement)<a href="https://agentmods.dev/commands/fmarzochi/egc/prp-implement"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/prp-implement/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/fmarzochi/egc/prp-implement"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/prp-implement.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 | $0.00008 | $0.00715 |
| Opus 5.5 | $0.00003 | $0.00286 |
| Sonnet 5.5 | $0.00002 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
prp-implement 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Executor
Input: $ARGUMENTS (plan file path, required)
Execute a plan file increment by increment under one non-negotiable rule: green to green. The repo is verified working before an increment starts and verified working when it ends. Broken state is never carried forward into the next increment.
Startup
- Read the plan file in full. If
$ARGUMENTSis blank or the file does not exist, list available plans inPRPs/plans/and stop. - Read every file in the plan's Context capsule.
- Find the first unchecked increment; this makes the command resumable after an interruption.
- Run the plan's validation commands once to establish the baseline. If the baseline is already red, stop and report: the plan assumed a green repo.
Increment loop
For each unchecked increment, in order:
- Apply: make the changes described, following the Mirror file's shape and the capsule's conventions.
- Validate: run the increment's Validate command exactly as written.
- Settle:
- Green: mark the increment's checkbox in the plan file, then continue.
- Red: enter the failure protocol below.
Never start increment N+1 while increment N is red.
Failure protocol
On a red validation:
- Read the full error output; fix the actual cause, not the symptom.
- Re-validate. If still red, try one structurally different approach (not the same edit again).
- Still red after the second attempt: stop. Revert the increment's changes so the repo returns to green, mark the increment as blocked in the plan file, and write a partial report (format below) describing what was tried and the exact error. Do not brute-force a third variation; a plan that fails twice has a wrong assumption that the user should see.
Completion
When every increment is checked:
- Run the full validation suite from the Context capsule (lint, typecheck, tests, build).
- Check the plan's "Done means" list item by item.
- Write the report to:
PRPs/reports/{plan-name}-report.md
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.
- 1mo ago First seen · 95 lines · 8 tokens per session scan A 35f8e872aac7
prp-implement is a command published in the GitHub repository Fmarzochi/EGC (68 stars, last pushed yesterday), licensed Apache-2.0. It adds 8 tokens to every session and 715 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 2026-09-03.
Other commands, from other repositories
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
test-management
Organize, classify, and trace Katalon True Platform/TestOps test assets. Use when you need to structure test cases into folders and suites, move or reorganize cases, search and find existing assets at scale, link or unlink requirements to test cases, or produce a requirement-to-test traceability report (which…
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.