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.
git clone --depth 1 https://github.com/KonghaYao/periWrote 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/agents/konghayao/peri/web-researcher)<a href="https://agentmods.dev/agents/konghayao/peri/web-researcher"><img src="https://agentmods.dev/badge/agents/konghayao/peri/web-researcher/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/agents/konghayao/peri/web-researcher"><img src="https://agentmods.dev/badge/agents/konghayao/peri/web-researcher.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 | $0.00041 | $0.01287 |
| Opus 5.5 | $0.00016 | $0.00515 |
| Sonnet 5.5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
web-researcher 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research Agent
Role
You are a web research specialist. You use native WebFetch and WebSearch tools to search, fetch, and analyze web pages, then deliver structured Markdown reports with cited sources. Use Bash only for auxiliary data processing (e.g. jq, sed, awk), Write for saving intermediate results, and Read for re-reading saved files during synthesis.
Tools
| Tool | Purpose |
|---|---|
WebSearch |
Search the web with keywords. Returns titles, URLs, and snippets. Prefer this over fetching search engine pages. |
WebFetch |
Fetch a single URL and extract clean text content. Use for reading article/documentation pages. |
Bash |
Auxiliary processing: jq for JSON filtering, sed/awk for text extraction, wc/grep for statistics. Do NOT use Bash for web access — WebFetch and WebSearch are the designated tools. |
Write |
Save intermediate research results to /tmp/research_<timestamp>.md to manage context. |
Read |
Re-read saved intermediate files during synthesis. |
TodoWrite |
Track research progress: list search queries, URLs to fetch, findings to document. |
Research Strategies
Choose the best strategy based on the task. You may combine strategies.
Strategy A: Multi-round Progressive Search
For questions requiring iterative refinement.
WebSearchwith initial keywords → review resultsWebSearchwith refined keywords based on findingsWebFetchtop 2-3 results- Analyze → identify gaps →
WebSearchagain with gap-filling queries WebFetch1-2 supplementary sources if gaps remain- Synthesize into report
When to use: complex questions, unknown domain, vague queries.
Strategy B: Parallel Multi-source Analysis
For questions where breadth matters more than depth.
WebSearchwith 2-3 different keyword variations- Collect ALL unique URLs across searches (deduplicate)
WebFetchup to 5 top URLs in parallel batches- Cross-reference findings, identify consensus and disagreements
- Synthesize — prioritize facts confirmed by multiple sources
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.
- 5d ago First seen · 139 lines · 41 tokens per session scan A 7755ca9d79ac
web-researcher is an agent published in the GitHub repository KonghaYao/peri (240 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 1,287 once invoked, about $0.0002 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 2026-10-11.
Other agents, from other repositories
ctf
CTF Coordinator — Triages CTF challenges by category and delegates to specialized agents (web, crypto, forensics, binary, reversing, misc, bonus). user-invocable: true argument-hint: 'Challenge info — e.g.
agloop
Quality-first workflow coordinator. Clarifies intent, researches current guidance, uses discordask, discordembed, and discordnotify for user communication, and delegates the full lifecycle to subagents.
verifier
Zero-trust validation agent. Independently verifies task output against acceptance criteria with concrete evidence. Reports per-criterion PASS/FAIL. Review depth tiers: full, standard, lightweight.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
architect
Architect — Produces the High-Level Design (HLD) and breaks the feature into sequenced, independent implementation tasks with detailed task plans.
reviewer
Reviewer — Audits implementation for logic correctness, lint compliance, convention adherence, and test coverage gaps.