fix

A command that finds and applies only predefined, safe fixes in a repository.

In plain words
What is it for?
Use it to create missing evidence files or test stubs, update .gitignore entries, fill evidence templates, and verify the results.
Why use it?
It removes small maintenance tasks while avoiding business-logic changes and other risky edits. A dry-run option lets you preview the changes first.

Command

Install

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.

agentmods
npx agentmods add commands/logi-cmd/agent-guardrails/fix
Clone the repo
git clone --depth 1 https://github.com/logi-cmd/agent-guardrails
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00324
Opus 5 $0.00005 $0.00162
Sonnet 5 $0.00002 $0.00065
Haiku 4.5 $0.00001 $0.00032

Measured 2d ago against content hash 08467151c038, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

templates/commands/fix.md · 60 lines

What it actually says

/ag:fix - Auto-Fix

Triggers

  • Guardrail check found issues
  • User wants to fix safe issues automatically
  • User types /ag:fix

Context Trigger Pattern

/ag:fix [--dry-run]

Default behavior: Apply Tier-1 auto-fixes (safe, reversible)

Behavioral Flow

  1. Scan: Run guardrail check to identify fixable issues
  2. Filter: Only Tier-1 fixes (safe, reversible)
  3. Preview: Show what will be fixed
  4. Apply: Execute fixes with rollback capability
  5. Verify: Re-check after fixes applied

Fixable Issues (Tier 1)

  • ✅ Missing evidence file → Create it
  • ✅ Missing test stub → Create stub
  • ✅ .gitignore not updated → Add entries
  • ✅ Empty evidence sections → Populate templates

Examples

Auto-fix

/ag:fix
# Scans for Tier-1 issues and applies fixes

Dry run

/ag:fix --dry-run
# Shows what would be fixed without applying

Boundaries

Will:

  • Fix safe, reversible issues
  • Show preview before applying
  • Rollback if fix fails

Will Not:

  • Fix business logic issues
  • Modify source code
  • Override user-specified constraints
Changes

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.

  1. 2d ago First seen · 60 lines · 10 tokens per session scan A 08467151c038

Subscribe to this mod's changes

fix is a command published in the GitHub repository logi-cmd/agent-guardrails (29 stars, last pushed 17d ago), licensed MIT. It adds 10 tokens to every session and 324 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 2026-08-30.