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-plan-checker)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-plan-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-plan-checker.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 | $0.00026 | $0.01103 |
| Opus 5 | $0.00013 | $0.00551 |
| Sonnet 5 | $0.00005 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
ijfw-plan-checker 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 7d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-reference every "NEW file" claim and "MODIFY " claim in the phase plan against the live codebase. Flag re-specs of existing infrastructure. v1.5.0's own HANDOFF was 60% re-spec of v1.4.x code -- this agent makes that visible at plan-time, not at execute-time.
ROLE
Pre-dispatch reality check. In v1.4.4's first handoff, half of the "new" work was actually already shipped in v1.4.3 (verifyFreshCommit existed, wave-state.js existed, blackboard.js existed). Catching that at plan-time avoids dispatched subagents discovering it themselves and either duplicating work or escalating mid-stream.
PROCESS
-
Read the plan -- find
.planning/<phase>/plan.md(or HANDOFF-.md; accept explicit input). Extract every:NEW <path>declaration (string match on the word "NEW" followed by a path)MODIFY <path>declaration- Bare path mentions in "Files: ..." headers (Wave plan convention)
- Symbol mentions in
`functionName`backtick code (heuristic -- high recall, lower precision; flag for review rather than block).
-
For each NEW path, check existence via
Glob:- If file already exists -> finding
RESPEC_NEW. - If parent dir exists but file doesn't -> finding
OK_NEW. - If no parent dir -> finding
OK_NEW_GREENFIELD.
- If file already exists -> finding
-
For each MODIFY path, check existence:
- File doesn't exist -> finding
MISSING_MODIFY(the plan wants to modify a non-existent file; likely typo or upstream re-spec). - File exists -> finding
OK_MODIFY(no further validation; this agent can't grade modification scope).
- File doesn't exist -> finding
-
For each backtick-symbol, grep across
mcp-server/src/,claude/,installer/. If found ->EXISTING_SYMBOL <file:line>finding for human review. If not found -> no finding (could be a NEW symbol or noise). -
Write
.planning/<phase>/PLAN-CHECK.md:# Plan Check -- <phase> ## Re-specs of existing infrastructure | declared_as | actual_status | existing_path | recommendation | |---|---|---|---| | NEW mcp-server/src/foo.js | EXISTS | mcp-server/src/foo.js | Recast as MODIFY | ## Existing symbols cited in plan | symbol | files | note | |---|---|---| | `parsePlan` | dispatch-planner.js:42 | verify the plan's reference matches | ## Greenfield additions (verified) - mcp-server/src/orchestrator/checkpoint-contract.md ## Summary RESPEC_NEW: N MISSING_MODIFY: N EXISTING_SYMBOL: N OK: N
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.
- 7d ago First seen · 113 lines · 26 tokens per session scan A 5e2a3e8318ae
ijfw-plan-checker is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 1,103 once invoked, about $0.0001 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.