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 FerroxLabs/ijfw --skill ijfw-debuggit 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/skills/ferroxlabs/ijfw/ijfw-debug)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-debug"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-debug.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 | $0.00031 | $0.00555 |
| Opus 5 | $0.00015 | $0.00278 |
| Sonnet 5 | $0.00006 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
ijfw-debug 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 yesterday.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1 -- Reproduce
State the failure in one line: what was expected vs. what happened. Confirm reproducible before proceeding. If intermittent, note conditions.
Step 2 -- Check recent changes
Call ijfw_memory_recall with the symptom. Scan .ijfw/memory/ for decisions or
changes from the past 7 days that touch the affected area.
If a recent change correlates with the regression, offer revert first:
Regression likely from <change> on <date>. Revert first? (y/n)
Step 3 -- Isolate
- Narrow to the smallest reproducing case (file, function, line range).
- Determine if failure is input-dependent, environment-dependent, or logic-dependent.
- Read only the specific lines relevant to the hypothesis. No full-file reads.
Step 4 -- Hypothesize
List hypotheses ranked by likelihood:
H1 -- <most likely cause> -- evidence: <why>
H2 -- <next candidate> -- evidence: <why>
H3 -- <edge case> -- evidence: <why>
Confirm H1 before testing H2.
Step 5 -- Fix and Verify
Apply the minimal change that addresses the root cause.
Do not fix adjacent issues -- log them as follow-ups.
Run tests/linter after every fix.
Confirm the original symptom is gone and no adjacent regression introduced.
Store result: ijfw_memory_store: <what broke>, <root cause>, <fix applied>
Step 6 -- Two-strikes session reset
If two attempts at root-cause fixes both fail to clear the original symptom, stop. Do not try a third on the same hypothesis tree. Summarize in three lines: what you tried, what each attempt revealed, what you now believe is true. Then ask the user:
Two attempts didn't land it. Recommend resetting this session and starting fresh with: "<sharpened prompt>". Accumulated failed context degrades the next attempt; a fresh session with a tighter brief usually clears it on the first try.
Capture the summary in ijfw_memory_store so the next session inherits the lessons without inheriting the noise.
Output format
SYMPTOM: <one line>
ROOT CAUSE: <H1 confirmed or revised>
FIX: <what changed + file:line>
VERIFIED: yes / needs more testing
FOLLOW-UPS: <any adjacent issues deferred>
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.
- yesterday First seen · 53 lines · 31 tokens per session scan A 8f772a012c26
ijfw-debug is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 555 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 2026-09-05.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
bug-fixer
name: bug-fixer description: Used when the user says "this feature is broken", "getting an error", "something's not right", or reports a bug, compilation error, or runtime exception. Locates root cause through a four-stage systematic debugging process and fixes it. version: 1.2.0 updated: 2026-06-27 requires: [].
reqforge-greenkeeper
name: reqforge-greenkeeper description: Used when maintaining the ReqForge repository itself and its release gates fail — pnpm test, pnpm forge-smoke, pnpm sync:discover, adapter drift, skill fixtures, loadouts, or test-demo golden path. Restores a green, synced state with minimal changes. Not for bugs in user apps…
repo-consistency-sweep
Proactive defect-class detection that handles the lower-value half of code review (per Bacchelli and Bird 2013) so human reviewers stay focused on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability…