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/Fmarzochi/EGCWrote 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/fmarzochi/egc/engineering-fix)<a href="https://agentmods.dev/commands/fmarzochi/egc/engineering-fix"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/engineering-fix/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/fmarzochi/egc/engineering-fix"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/engineering-fix.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 | $0.00048 | $0.01207 |
| Opus 5 | $0.00024 | $0.00603 |
| Sonnet 5 | $0.00010 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
engineering-fix 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 5d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Fix
Input: $ARGUMENTS
Applies the remediation plan produced by /engineering-audit. Operates exclusively on an isolated branch. Never modifies files directly on the current branch. Always requires explicit user confirmation before starting.
Pre-conditions
Before running any fix:
- Confirm audit exists:
ls .egc/audits/engineering-audit-*.md 2>/dev/null | sort | tail -1
If no audit report exists, stop: "Run /engineering-audit first."
- Confirm working tree is clean:
git status --porcelain
If uncommitted changes exist, stop: "Stash or commit your changes before running engineering-fix."
- Confirm user intent: print the scope and ask explicitly:
Ready to apply engineering fixes.
Scope: <CRITICAL only | CRITICAL + HIGH | etc. based on $ARGUMENTS>
Branch: engineering-fix/<date>
Files to modify: N
This will:
1. Create branch engineering-fix/<date>
2. Apply each fix incrementally
3. Run lint + typecheck + tests after each file
4. Revert and stop if any check fails
Confirm? (yes / no)
Do NOT proceed without a "yes" response.
Argument Handling
| Argument | Behavior |
|---|---|
--severity critical |
Apply CRITICAL fixes only (default) |
--severity high |
Apply CRITICAL + HIGH fixes |
--severity medium |
Apply CRITICAL + HIGH + MEDIUM fixes |
--severity all |
Apply all findings |
--file <path> |
Apply fixes to one specific file only |
| blank | CRITICAL fixes only |
Execution
Step 1: Create Isolated Branch
git checkout -b engineering-fix/$(date +%Y-%m-%d)
Step 2: Load Remediation Plan
Read the most recent audit report:
cat .egc/audits/engineering-audit-$(ls .egc/audits/ | grep engineering-audit | sort | tail -1 | sed 's/engineering-audit-//' | sed 's/\.md//')
Extract the list of files and fixes matching the requested severity.
Step 3: Apply Fixes Incrementally
For each file in the plan (CRITICAL first, then HIGH, etc.):
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.
- 5d ago First seen · 179 lines · 48 tokens per session scan A 6c0202a84fdb
engineering-fix is a command published in the GitHub repository Fmarzochi/EGC (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,207 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 2026-09-03.
Other commands, from other repositories
fix-issue
Fetch a GitHub issue, find the relevant code, implement the fix, verify, and open a PR.
reqforge-greenkeeper
Diagnose and fix ReqForge repository release gate failures.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
bug-report-triage
Turn a vague bug report into a structured, actionable ticket with severity and next steps.
release-announcement
Announce a release so users know what changed, what breaks, and what to do about it.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).