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 theagenticguy/erpaval --skill researchgit clone --depth 1 https://github.com/theagenticguy/erpavalWrote 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/theagenticguy/erpaval/research)<a href="https://agentmods.dev/skills/theagenticguy/erpaval/research"><img src="https://agentmods.dev/badge/skills/theagenticguy/erpaval/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/theagenticguy/erpaval/research"><img src="https://agentmods.dev/badge/skills/theagenticguy/erpaval/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 | $0.00082 | $0.00738 |
| Opus 5.5 | $0.00033 | $0.00295 |
| Sonnet 5.5 | $0.00016 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contents
| Reference | When to load |
|---|---|
references/orchestrator.md |
Running /research <topic> — the full 5-phase flow |
references/write-protocol.md |
Copy verbatim into every agent prompt |
references/search-strategies.md |
Tool inventory, priority order, query patterns |
templates/agent-skeleton.md |
Per-agent Markdown file skeleton |
templates/synthesis-skeleton.md |
Synthesis output skeleton |
Research
A single-mode research orchestrator. Runs inside a forked subagent so the main conversation stays clean. Decomposes the question, launches 2–4 Opus 4.7 agents in parallel with a file-first write protocol, monitors progress by reading their files, recovers stuck agents, and then runs one synthesis pass to produce the final brief.
How it works
Read references/orchestrator.md and follow its phases. The short version:
- Plan — decompose into 2–4 workstreams with non-overlapping scopes and 3–6 sections each. Present plan. Wait for approval.
- Skeletons — create
research/{slug}/and write a file per agent plus a synthesis file, each starting withStatus: IN PROGRESS. - Launch — fire all research agents in one message as parallel
Agentcalls withmodel: "opus"andrun_in_background: true. - Monitor — escalating check-ins (30s → 2m → 5m).
wc -lper file to track progress. If an agent's line count stalls across two checks, launch a freshAgentwith the existing file state and a "skip these sections" prompt. - Synthesize — one foreground
Agentreads every agent file and writessynthesis.mdwith themed findings, contradictions, confidence, gaps, next steps, and deduplicated sources.
Write discipline
Every agent prompt carries the write protocol verbatim from references/write-protocol.md: one search or fetch → edit the file with findings → next search. This keeps partial progress on disk where it survives timeouts and 403 errors.
What ships with it
5 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.
- 1mo ago First seen · 54 lines · 82 tokens per session scan A 17fd1d911596
research is a skill published in the GitHub repository theagenticguy/erpaval (28 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 738 once invoked, about $0.0003 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
engine-bootstrap
Use when no contextualizer exists yet for a set of source URLs or local paths and one needs to be scaffolded from scratch.
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
using-skill-engine
When the user mentions skill-engine or "the engine" without naming a specific workflow, or wants first-run setup. Inspects .claude/skills/-context/ install state (and any pending -context.proposed/ proposals) across all three install levels, then dispatches to engine-bootstrap when no contextualizer exists, to…
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.
config-set
Use when changing an engine-wide config value — currently diff.tool, the command /skill-engine:review prints for inspecting a proposed-vs-live diff.
inspect-ai-context
Answers questions across the configured sources. References load on demand from references/. Use when working in any of this contextualizer's source domains.