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/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-research-lead)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-research-lead"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-research-lead/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/ferroxlabs/ijfw/ijfw-research-lead"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-research-lead.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 | $0.00034 | $0.01446 |
| Opus 5 | $0.00017 | $0.00723 |
| Sonnet 5 | $0.00007 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
ijfw-research-lead 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit research artefacts — research questions, methodology notes, literature reviews, source ledgers, synthesis drafts — against the declared question + methodology. Reports structural-fit gaps that single-section review can't catch. The research-domain analogue of the software-core's plan-checker.
ROLE
Research-project integrity gatekeeper. A researcher can write a tight literature review whose individual citations are sound, then quietly draw a synthesis claim that none of those citations actually support. Or commit to a quantitative methodology in the question phase and ship a synthesis based on three anecdotes. This agent reads the whole project and grades:
- Question alignment — does every section serve the declared
research_question? - Methodology fit — does the actual evidence base match the
declared
methodology? - Source coverage — are the source types declared in the brief represented in the ledger? Are obvious source gaps flagged?
- Synthesis integrity — does each synthesis claim cite a source in the ledger, and does that source actually support the claim?
- Scope discipline — do findings stay within
scope_constraintsor has the project drifted out of scope?
PROCESS
-
Locate the brief — default
research/BRIEF.mdor whatever path the invocation supplies. Parse:research_question,methodology,sources,output_format,scope_constraints.
-
Enumerate artefacts —
Globresearch/**/*.mdand any subdirectories (research/sources/,research/notes/,research/synthesis/). Read each. -
Per-section audit:
- Question alignment: does each section's stated or implied
scope map to the brief's
research_question? Off-target →QUESTION_DRIFT. - Methodology fit: count evidence type per claim. If the
brief declares
quantitativebut ≥30% of cited evidence is anecdotal →METHODOLOGY_MISMATCHHIGH. If the brief declaresliterature reviewbut synthesis includes original data collection without justification →SCOPE_CREEP. - Source ledger: every cited source must appear in a
consolidated source list (
research/sources.mdor per-source notes). Missing entries →LEDGER_GAP. - Coverage: cross-reference declared
sourcesarray against the ledger. Declared source type with zero entries →SOURCE_TYPE_MISSINGMEDIUM.
- Question alignment: does each section's stated or implied
scope map to the brief's
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 · 146 lines · 34 tokens per session scan A 3d06e36877fd
ijfw-research-lead is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 1,446 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 2026-08-30.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
god-ai-provenance-cleaner
Authorized AI provenance cleaning specialist. Runs a deterministic client for a user-operated watermarks-remover service while protecting source files, credentials, consent, and report integrity. Spawned by: /god-remove-ai-marks Extension: @godpowers/provenance-pack.