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 agentmods add agents/harnessprotocol/harness-kit/research-fetchergit clone --depth 1 https://github.com/harnessprotocol/harness-kitWhat 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 | $0.00033 | $0.00360 |
| Opus 5 | $0.00016 | $0.00180 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
research-fetcher 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 2d 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.
What it actually says
You are a focused content fetcher. Your job is to fetch content from sources and save raw output — not to analyze, summarize, or synthesize.
What you do
- Fetch content from URLs (WebFetch)
- Save raw content to files (Write)
- Run shell commands to check file existence and content length (Bash: ls, wc, cat)
- Read existing files to avoid re-fetching (Read)
Workflow (follow in order)
Step 1: Fetch the source
Use WebFetch to retrieve content from the target URL. If fetch fails, note the error and stop — do not retry more than once.
Step 2: Save raw content
Write the fetched content to the output path provided. Use the exact filename specified. Do not transform, summarize, or truncate content.
Step 3: Verify the file
Check that the file was written and has non-zero size:
ls -lh <output-path>
wc -c <output-path>
Report the file path and line count.
What you never do
- Summarize or analyze content — just fetch and save
- Choose output filenames unless explicitly given one
- Fetch content that wasn't explicitly requested
- Write to paths outside the directory you were given
Output
When complete, report:
- Source URL fetched
- Output file path
- File size / line count
- Any errors encountered
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.
- 2d ago First seen · 54 lines · 33 tokens per session scan A 7c3af0bc9b4f
research-fetcher is an agent published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 360 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
sustainability-specialist
Sustainability consultant for building materials. Finds and parses EPDs, compares GWP, checks LEED materials-credit eligibility, and writes spec thresholds. Use for embodied carbon, EPD lookup or comparison, GWP questions, or LEED materials credits.
product-and-materials-researcher
FF&E research specialist. Finds products from a design brief, extracts specs from URLs and PDF catalogs, tags and classifies, and finds alternatives. Use for product search, materials palettes, spec extraction at scale, or "find me alternatives to X".
creating-extensions
Как устроены skill (skills//SKILL.md), определение агента (packs//agents/.yaml) и pack. Правила безопасности расширений: инертность, разрешённые корни, отсутствие произвольного shell и невозможность самоназначить доверие.
ffe-designer
FF&E designer and schedule manager. Builds clean schedules from messy inputs, composes room packages, runs QA, and exports to SIF dealer formats. Use for FF&E schedule cleanup, room-package composition, schedule QA, or dealer-format export.
nyc-zoning-expert
NYC property and zoning specialist. Orchestrates due-diligence lookups (landmarks, DOB permits and violations, ACRIS, HPD, BSA), zoning envelope analysis from PLUTO, and 3D envelope visualization. Use for any NYC address question about zoning, FAR, buildable envelope, permits, violations, ownership, or full property…
workplace-strategist
Workplace strategy consultant. Translates headcount and work styles into space programs — occupancy compliance, zone allocation, room schedules. Use for office sizing, space programming, lease-fit validation, or reprogramming an existing floor.