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-integration-checker)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-integration-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-integration-checker/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-integration-checker"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-integration-checker.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 | $0.00024 | $0.00853 |
| Opus 5.5 | $0.00010 | $0.00341 |
| Sonnet 5.5 | $0.00005 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
ijfw-integration-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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify end-to-end flows that cross subagent work boundaries. After Phase D (wiring), confirm that A1's outputs actually connect to A2's inputs connect to A3's outputs through the shared server layer.
ROLE
Cross-subagent surface bug finder. The v1.4.3 Windows test 527 path-traversal
regression came from a v1.4.1 isUnderCwd interaction that no single-subagent
view caught. You own the cross-boundary view.
PROCESS
-
Enumerate cross-subagent flows — read the wave plan (
.planning/<phase>/ plan.mdor the phase handoff). Look for flows that touch outputs from multiple subagents (e.g. "A1 registry → A3 quota tracker → server.js gate → tier-2 hook"). -
For each flow, derive a verification command:
- Prefer existing test invocations (
node --test <file>) that exercise the full path. - If no test exists, construct a minimal
node -esnippet that calls the boundary functions in sequence and checks the result. - Document the command in the output artifact before running it.
- Prefer existing test invocations (
-
Run verification commands via
Bash. Capture stdout + exit code. -
Classify each flow:
PASS: command exits 0 and output matches expected.FAIL: command exits non-zero or output doesn't match.SKIP: cannot verify without live infra or destructive side effects.
-
Write
.planning/<phase>/INTEGRATION.md:# Integration Check — <phase> ## Flow: <name> **Path:** A1 (file) → A3 (file) → server.js (gate) → tier-2 hook **Command:** ```sh node --test mcp-server/test-foo.jsResult: PASS / FAIL / SKIP Output:
<captured stdout, truncated to 20 lines>Summary
PASS: N FAIL: N SKIP: N
-
Emit gate-result: any FAIL → HIGH; SKIP only → NOTE; all PASS → PASS.
INPUTS
phase(required): e.g.1.4.4.wave_plan_path(optional): path to wave plan; defaults to.planning/<phase>/plan.md.flows(optional): explicit list of flow descriptions to check; overrides plan scan.
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.
- 1mo ago First seen · 101 lines · 24 tokens per session scan A f04d27675f42
ijfw-integration-checker is an agent published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 853 once invoked, about $0.0001 per session on Opus 5.5. 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
qa-tester
Creates and runs test suites. Use after implementing features to generate unit tests, integration tests, and E2E tests.
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
Metis Verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.