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 skills add FarzamMohammadi/the-engineer --skill implementgit clone --depth 1 https://github.com/FarzamMohammadi/the-engineerWrote 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/farzammohammadi/the-engineer/implement)<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/implement"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/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/skills/farzammohammadi/the-engineer/implement"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/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 | $0.00206 | $0.02475 |
| Opus 5.5 | $0.00082 | $0.00990 |
| Sonnet 5.5 | $0.00041 | $0.00495 |
| Haiku 4.5 | $0.00021 | $0.00248 |
Grade A, and why
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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
You own the outcome. Requirements gathered intent, research mapped the ground, the plan recorded the decisions — now you turn that plan into working, verified, gap-free code. This is the "I" of RRPIR.
You do this in a specific way, and the way is the point. You always orchestrate the build through agent workflows — you do not hand-type the whole thing yourself — and then you take the wheel as the co-owner: the build is not done when the agents report done; it is done when you have verified it against the plan and there is not a single gap, bug, or loose end left. Two hats, in order: first the orchestrator who gets the work built, then the owner who proves it and closes it out.
This is not /review. Review is a separate, optional, independent quality gate (coverage analysis, a dedicated bug-hunt, a manual-testing checklist, MR prep) the user may run afterward — and may not. Your verification here is narrower and load-bearing in a different way: confirming that the orchestrated build delivered the approved plan, completely and correctly, and personally closing whatever it missed. Don't reproduce the review process; own the implementation to done.
Phase 1: Absorb the plan
Read every upstream artifact in full before launching anything:
- The plan —
.claude/temp/create-plan/ - Research —
.claude/temp/research/— and requirements —.claude/temp/requirements-gathering/
Internalize the decisions, the task breakdown, the verification contract, the scope boundary, and the risks. You have to own this material deeply: you cannot orchestrate what you haven't grasped, and you cannot later verify a plan you only skimmed. If the plan has a gap, or the codebase has drifted since it was written, surface that to the user now — before agents start writing against a stale map.
Phase 2: Orchestrate the build (always — even when it's one workflow)
Hand the execution to the /workflow-orchestrator skill's method (its Phase 3 — Orchestrate). The implementation always runs through orchestrated agents, even when the right answer is a single workflow that spawns a single agent.
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 · 148 lines · 206 tokens per session scan A 81e1205feafa
implement is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 3mo ago), licensed MIT. It adds 206 tokens to every session and 2,475 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
release-cut
Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
spec-coherence-check
Sweep all active OpenSpec proposals for staleness, conflicts, and obsolescence against the current codebase and archived changes. Use when proposals may be outdated, when checking cross-proposal conflicts, or before starting a batch of implementations. Produces a gap-analysis report, updates a priority queue file, and…
deck3d
Build a self-contained 3D presentation from a Markdown outline — parse, tune via overrides, render to one offline deck.html. Use on "make a 3D deck from this outline", "build a presentation from these notes", "deck3d this markdown", "turn this talk into a 3D deck".