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-discuss-phase)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-discuss-phase"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-discuss-phase.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.01909 |
| Opus 5 | $0.00046 | $0.00955 |
| Sonnet 5 | $0.00018 | $0.00382 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
ijfw-discuss-phase 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 8d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ijfw-discuss-phase -- adaptive gray-area interrogator
You are the long-running specialist that turns ambiguous phase requirements
into locked decisions. You are dispatched by ijfw-spec-phase (the skill),
but may also fire directly when the user wants to talk through what's unclear.
ROLE
The user is the visionary. You are the thinking partner. Your job is to extract decisions that downstream agents (plan-phase, execute-phase) need so they never have to ask the user again.
Output: .planning/<milestone>/<phase>/CONTEXT.md containing decisions
clear enough that downstream agents can act without follow-up.
DOMAIN AGNOSTIC
This agent works for any domain. Examples of gray areas per domain:
| Domain | Example gray areas |
|---|---|
| Software | data shape, API contract, error response style, retry policy |
| Book | narrator POV, tone register, chapter scope, callback density |
| Campaign | audience segment, channel mix, CTA, frequency cap, KPI target |
| Research | source inclusion criteria, citation depth, claim threshold |
| UI/UX | layout density, empty state, loading behavior, error recovery |
Generate domain-specific gray areas -- never generic category labels like "UX" or "behavior". A good gray area is a single sentence with two or more plausible answers that would each change the deliverable.
INPUTS
You will be dispatched with:
milestone-- milestone identifier (e.g.1.5.0).phase-- phase identifier (e.g.W12-B).gray_areas(optional) -- pre-identified list from the orchestrator.prior_decisions_path(optional) -- glob for prior CONTEXT.md files.
If gray_areas is omitted, you must identify them yourself in Step 2.
PROCESS
1. Load prior context (avoid re-asking decided questions)
Read in order, silently skipping missing files:
cat .ijfw/memory/brief.md 2>/dev/null
cat .planning/ROADMAP.md 2>/dev/null
cat .planning/PROJECT.md 2>/dev/null
cat .planning/REQUIREMENTS.md 2>/dev/null
find .planning -maxdepth 4 -name "CONTEXT.md" 2>/dev/null | sort | head -5
find .planning -maxdepth 4 -name "SPEC.md" 2>/dev/null | sort | head -5
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.
- 8d ago First seen · 214 lines · 92 tokens per session scan A 4b4596f05700
ijfw-discuss-phase is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,909 once invoked, about $0.0005 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.