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 forger-labs-hq/researchforge --skill researchforge-startgit clone --depth 1 https://github.com/forger-labs-hq/researchforgeWrote 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/forger-labs-hq/researchforge/researchforge-start)<a href="https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-start"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-start/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/forger-labs-hq/researchforge/researchforge-start"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-start.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 | $0.00051 | $0.00714 |
| Opus 5 | $0.00026 | $0.00357 |
| Sonnet 5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
researchforge-start 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start or resume a ResearchForge project
ResearchForge is a local CLI: Claude proposes (queries, syntheses, patches);
the Python engine validates, executes, and records. Every command supports
--json — prefer it and read the structured output instead of parsing prose.
Resume an existing project
Always check state first:
researchforge status --json
The next_action field names the exact next command. Follow it — the engine
tracks the pipeline (papers → landscape → hypotheses → contract → baseline →
experiments → validation → shipping) and will not let steps run out of order.
Summarize where the project stands from the JSON counts, then invoke the
matching skill (researchforge-papers, researchforge-baseline, …).
Start a new project
- Ask where the project should live. ResearchForge is directory-scoped:
the database, worktrees, artifacts, and dashboard all live under the
directory you run it in — any folder works, it does not have to be a
repository you already opened. If the user names a folder (e.g. "do all
experiments at ~/Desktop/some_new_folder"), either
cdthere or prefix every command withresearchforge -C <folder> …. Confirm the location back to the user;researchforge pathsprints the full map afterwards. Commands run in a subfolder of a project walk up to the project root automatically (aUsing project at <root>note appears on stderr). Tell the user their project appears in the hub at http://127.0.0.1:9000 (all projects on the machine, with folder locations). - Ask the user which journey they want:
- Explore a research idea — literature search, landscape, hypotheses,
citation-backed report. Mode:
explore_research_idea. - Improve a repository — everything above plus a frozen baseline and
benchmarked experiments on their code. Mode:
improve_repository.
- Explore a research idea — literature search, landscape, hypotheses,
citation-backed report. Mode:
- Ask for a one-sentence objective (for
improve_repositoryit should name the metric to improve, e.g. "Improve classification F1 without increasing latency"). - Run:
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.
- 9d ago First seen · 71 lines · 51 tokens per session scan A 6ba84cefcf4a
researchforge-start is a skill published in the GitHub repository forger-labs-hq/researchforge (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 51 tokens to every session and 714 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 2026-08-31.
Other skills, from other repositories
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
statistical-method-design
Design statistical methods, baselines, diagnostics, variants, and ablations that directly address a formal problem formulation.
experimental-design
Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.