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 commands/fmarzochi/egc/prp-implementgit 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.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 | $0.00008 | $0.00715 |
| Opus 5 | $0.00004 | $0.00358 |
| Sonnet 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 yesterday.
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.
- yesterday First seen · 95 lines · 8 tokens per session scan A 35f8e872aac7
prp-implement is a command published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 8 tokens to every session and 715 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
demand-discovery
Run automated niche demand discovery research across 7 data sources and 26 categories.
tdd-workflow
Implement the behavior described in $ARGUMENTS using strict TDD. Follow this exact sequence. Do not collapse phases. Each gate requires actual test runner output.
api-add-endpoint
Create a new API endpoint. $ARGUMENTS should describe the endpoint (e.g., "POST /api/users - create a user").
api-test-endpoint
Test the API endpoint specified in $ARGUMENTS.
code-review
Review the code changes in this project. For each file changed.
refactor-file
Refactor the file specified in $ARGUMENTS following project conventions.