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/sairam0424/MindForgeWrote 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/commands/sairam0424/mindforge/debug)<a href="https://agentmods.dev/commands/sairam0424/mindforge/debug"><img src="https://agentmods.dev/badge/commands/sairam0424/mindforge/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 | $0.00013 | $0.00944 |
| Opus 5 | $0.00006 | $0.00472 |
| Sonnet 5 | $0.00003 | $0.00189 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MindForge — Debug Command
Usage: /mindforge:debug [description]
Systematic debugging using the Debug Specialist persona with full RCA protocol.
Activation
Load .mindforge/personas/debug-specialist.md immediately.
This command runs entirely in that persona for its full duration.
Step 0 — Initial Intelligence Check
Read AGENTS_LEARNING.md before intake. Check the "Mistakes Observed" and "Anti-Patterns" sections to see if this issue matches a known historical failure.
Step 1 — Intake
Ask the user:
- "Describe the problem. What is happening vs. what should happen?"
- "Can you reproduce it reliably? If yes: what are the exact steps?"
- "When did this start? Was it working before? What changed?"
- "Do you have an error message or stack trace? Paste it here."
Capture all answers before proceeding.
Step 2 — Triage
Classify the issue immediately:
- Regression (was working, now broken) → check recent commits
- Never worked (new feature failing) → check the plan and verify step
- Environment issue (works locally, fails in CI) → check environment diffs
- Data issue (specific data causes failure) → check data shape assumptions
- Integration issue (fails when calling external service) → check contracts
Report classification to user: "This looks like a [type] issue. Here's my approach..."
Step 3 — Follow Debug Specialist protocol
Execute the full protocol from debug-specialist.md:
- Reproduce
- Isolate
- Read the error
- Check recent changes
- Instrument
- Form hypothesis
- Test hypothesis (write a failing test)
- Fix
- Verify (test from step 7 now passes, no regressions)
- Document
At each step, report what was found before moving to the next step. Do not skip steps or combine them.
Step 3b — Full test suite verification (mandatory)
After the fix and targeted verify pass, run the project's full test suite. Do not mark the debug task complete if any tests fail.
Step 4 — Check recent git history
git log --oneline -20
git diff HEAD~[N] HEAD -- [suspected file]
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.
- 4d ago First seen · 134 lines · 13 tokens per session scan A c9755e1eba31
debug is a command published in the GitHub repository sairam0424/MindForge (0 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 944 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 2026-09-03.
Other commands, from other repositories
factory-retro
Find what is repeatedly wasting the factory's time and fix the harness, not the symptom.
debug
Run a 4-phase systematic debugging investigation before proposing any fix. Iron Law — NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a .orchestrator/debug/ artifact the fixer agent must reference.
p6-bugfix
Fixes bugs and vulnerabilities found during the QA phase (functional tests, exploratory tests, accessibility check, security audit, pentest). Each fix is secured by a regression test.
p6-exploratory
Conducts unstructured, experience-based tests that automated tests and defined test cases do not cover. The goal is to find unexpected behaviours, usability issues, and hidden bugs that remain invisible in structured testing.
p8-ops
Analyses production errors and performance issues, evaluates incidents, and initiates countermeasures. Called reactively for specific incidents or proactively for regular operational reviews.
p6-pentest-logic
Tests manipulation of business logic: prices, quantities, race conditions, flow bypasses.