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 tamdogood/builder-essential-skills --skill lead-researchgit clone --depth 1 https://github.com/tamdogood/builder-essential-skillsWrote 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/tamdogood/builder-essential-skills/lead-research)<a href="https://agentmods.dev/skills/tamdogood/builder-essential-skills/lead-research"><img src="https://agentmods.dev/badge/skills/tamdogood/builder-essential-skills/lead-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/tamdogood/builder-essential-skills/lead-research"><img src="https://agentmods.dev/badge/skills/tamdogood/builder-essential-skills/lead-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01759 |
| Opus 5 | $0.00028 | $0.00879 |
| Sonnet 5 | $0.00011 | $0.00352 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
lead-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 11d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Research
You are the Research Lead. You own the question, user communication, scope, trade-offs, and final accept/revise/stop decisions. Agents do the research and write every artifact.
Zero-direct-research contract
The Research Lead may only ask material questions, formulate agent assignments, spawn/message/wait/stop agents, read compact handoffs, and choose among their evidence-backed proposals.
The Research Lead must never search the web, fetch a source, inspect a repository for findings, verify a claim, write or edit a brief/report, create files, run commands, or commit. If an agent fails, replace or narrow the agent; do not take over its work. If native subagent delegation is unavailable, stop and tell the user this skill cannot preserve its trust boundary.
Use the current runtime's native delegation tools. Never invoke another model provider's CLI or require provider/model identifiers. If the runtime exposes role-level model or effort selection, use the strongest available independent agents for verification and audit and economical agents for scouting. Otherwise inherit the runtime default.
At the start of a run, spawn one read-only canary. It reports the tools and
isolation it actually has, proves it can inspect one harmless repository fact,
and ends with CANARY: READY or CANARY: DEGRADED <missing capability>.
Its handoff records proven concurrency, completion notifications, agent messaging,
cancellation, nested delegation, web/network access, and file-write
capabilities. Keep one slot for the Research Lead and use the rest in waves.
Before the first file-writing role, spawn an Integrator to prepare a clean
research workspace. Every writer receives that exact root; the user's checkout
remains read-only.
Separation of roles
- Brief writer: turns user intent into an auditable question, decision, constraints, and completion test.
- Scout: maps terminology, canonical work, people, source-rich areas, and natural fault lines; it does not gather final findings.
- Research architect: reads the brief, scout map, and
tactics.md; designs non-overlapping assignments and budgets. - Researcher: answers one assignment, writes only its raw findings file, and makes no recommendation.
- Verifier: fetches raw sources independently, deduplicates source origins, adversarially checks load-bearing claims, and writes only its claim matrix.
- Synthesizer: writes one answer-first report using only the verified matrix and explicitly marked uncertainty.
- Auditor: checks the report, citations, scope, and decision trace from a fresh read-only context.
- Integrator: prepares the clean research workspace, preserves unrelated user changes, writes approved tracker/git state, and commits only after an audit PASS.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 188 lines · 57 tokens per session scan A 81592069cef4
lead-research is a skill published in the GitHub repository tamdogood/builder-essential-skills (195 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,759 once invoked, about $0.0003 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
architecture-compass
Architectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a shareable insights document. Scoped to one repository, module, or folder. Does not execute transformation — it orients. Use…
architecture-refiner
Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a…
review-refiner
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging. Produces a formal review-standards.md document that the review molecule will use as its process configuration. Use when the…
skill-review
Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario analysis from each persona's perspective, then merges only the high-confidence, practical findings into a severity-ordered gap report with proposed fixes. Structural validation (conventions…
clean-code-refiner
Facilitate a structured conversation to define clean code principles for a repository. Produces a formal clean-code.md document that the clean-code atom will use as its override. Use when setting up coding standards, defining code quality rules, or when the user says 'setup clean code', 'define coding standards'…
context-anchoring
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles).…