Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marcusgoll/Spec-Flownpx agentmods add commands/marcusgoll/spec-flow/debugWrote 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/marcusgoll/spec-flow/debug)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/debug"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/debug/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/commands/marcusgoll/spec-flow/debug"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/debug.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 | $0.00022 | $0.04143 |
| Opus 5.5 | $0.00009 | $0.01657 |
| Sonnet 5.5 | $0.00004 | $0.00829 |
| Haiku 4.5 | $0.00002 | $0.00414 |
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 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 — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debug — Systematic Error Resolution
Current Branch: !git branch --show-current 2>/dev/null || echo "none"
Feature Slug: !git branch --show-current 2>/dev/null | sed 's/^feature\///' || echo "unknown"
Recent Debug Sessions: !ls -1t specs/*/debug-session.json 2>/dev/null | head -3 || echo "none"
Recent Errors: !tail -20 specs/*/error-log.md 2>/dev/null | grep "^###" | head -3 || echo "none"
Git Status: !git status --short 2>/dev/null || echo "clean"
Debug Session Artifacts (after script execution):
- @specs/*/debug-session.json
- @specs//debug/run-XXXXXX/.log
- @specs/*/error-log.md
Execute debugging workflow by:
- Running centralized debug script with arguments: $ARGUMENTS
- Analyzing verification status (lint, types, tests)
- Reading log files if verification failed
- Presenting results with actionable next steps
- Updating error knowledge base (error-log.md)
Modes:
- Manual: User specifies error type and component (non-interactive by default)
- Structured: Auto-invoked by
/optimizewith issue metadata (--from-optimize)
Philosophy: Every error is a learning opportunity. Document failures, symptoms, root causes, and fixes. The error-log.md becomes the project's debugging knowledge base.
Workflow position: implement → debug → optimize → preview → ship
Anti-Hallucination Rules
CRITICAL: Follow these rules to prevent fabricating debug results.
-
Never claim script success without reading artifacts
- Always Read debug-session.json to verify status
- Quote actual verification result: "passed" or "failed"
- Cite log files: "See specs/my-feature/debug/run-abc123/pytest.log:45"
-
Always read log files if verification failed
- Don't guess at errors - read actual log content
- Quote verbatim error messages with file:line references
- Show stack traces or lint errors from logs
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 · 508 lines · 22 tokens per session scan A 2832d12e8f5a
debug is a command published in the GitHub repository marcusgoll/Spec-Flow (96 stars, last pushed 23d ago), licensed MIT. It adds 22 tokens to every session and 4,143 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 commands, from other repositories
fixme
Looks for all the fixme comments in the code and attempts to fix them.
heal
Self-healing orchestration. Diagnose F2/F3 failures, view proposals, accept/decline, disable.
check
Verify code quality, security, performance, and coverage. One command to audit everything.
cleaning
A command for inspecting and safely cleaning a project or an entire server, including unused code, duplicates, conflicts, and leftover files.
bug-report
Structured bug-fix protocol per docs/methodology/bug-protocol.md. Use when asked to '/bug-report', 'I found a bug', 'something is broken', 'fix this bug', 'report a bug', 'this is broken'.
debug
A debugging command that traces a failure back to its underlying cause before suggesting one fix.