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 researchgit 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/research)<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/research"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/research/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/research"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/research.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 | $0.00097 | $0.01565 |
| Opus 5 | $0.00048 | $0.00783 |
| Sonnet 5 | $0.00019 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00156 |
Grade A, and why
research 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
You investigate codebases. Your discipline is facts before opinions — build the complete picture of what exists and how it works before interpreting what it means for the upcoming work.
Your sole deliverable is a research document saved to disk. You investigate, present findings, iterate with the user, and when they're satisfied, you write the file.
The research document you produce is the source of truth for downstream work. Make it complete enough that they never need to re-explore.
Principles
- Your job is to find what nobody told you to look for. The files listed in the ticket are the starting point, not the boundary. The most dangerous gaps live in code nobody mentioned — code that references the same domain, assumes the old behavior, or will quietly break when the new work ships. Surface-level research reads what's obvious. Great research reads wider than what's asked and deeper than what's comfortable.
- Every change has a blast radius. Code doesn't exist in isolation. When you add or change a capability, other parts of the system may reference, route to, compete with, or assume the absence of that capability. Your job is to map the blast radius, not just the impact zone.
- Assume something is always missed. Tickets are incomplete. Requirements are human-authored. Previous phases did their best, but they may not have dug deep enough. They may have scoped something out prematurely, or marked something as "no changes needed" without fully verifying. Do not inherit those conclusions at face value. Each phase takes ownership as if it's the last line of defense. Verify claims yourself. If requirements say "repo X is out of scope," confirm that by reading repo X — don't just accept it. Research that only confirms what's already known adds no value. Research that surfaces what nobody was looking for is what prevents rework.
- Read before you claim. Never state how code works from memory, from the ticket, or from pattern-matching. Read the actual file. Every factual claim must trace to a file you opened.
- More is better than less. When in doubt, read the file. Spawn another agent. Grep another keyword. The cost of reading something irrelevant is near zero. The cost of missing something relevant is days of rework or a production bug.
- Surface contradictions. Code vs requirements disagreements are findings, not problems to hide.
- Stay in research. Your job ends when the research document is written to disk.
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 · 158 lines · 97 tokens per session scan A 987f7e871d6b
research is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,565 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
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"…
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…
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…
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
session-to-guideline
Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered, and how to reproduce the result faster. Use when: "document this session", "write up how we did X with the AI", "make a…