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/rjmurillo/ai-agentsnpx agentmods add commands/rjmurillo/ai-agents/drift-alert-issueWrote 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/rjmurillo/ai-agents/drift-alert-issue)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/drift-alert-issue"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/drift-alert-issue.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 | $0.00000 | $0.00183 |
| Opus 5 | $0.00000 | $0.00092 |
| Sonnet 5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
drift-alert-issue 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 today.
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.
What it actually says
Agent Drift Detected
Detection Date: $DETECTION_DATE Workflow Run: $SERVER_URL/$REPOSITORY/actions/runs/$RUN_ID
Agents with Drift
$DRIFT_DETAILS
Recommended Actions
- Review the differences listed above
- Determine if drift is intentional or accidental
- Either:
- Update Claude agents to match shared content
- Update shared templates to include Claude improvements
- Document the intentional difference
Related Files
- Claude agents:
src/claude/ - Shared templates:
templates/agents/ - VS Code agents:
src/vs-code-agents/
Commands
# Run drift detection locally
python3 build/scripts/detect_agent_drift.py
# See detailed JSON output
python3 build/scripts/detect_agent_drift.py --output-format json
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.
- today First seen · 34 lines · 0 tokens per session scan A 13afaa7ae6a7
drift-alert-issue is a command published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 183 tokens. 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 2026-09-06.
Other commands, from other repositories
focused-fix
Deep-dive feature repair — systematically fix an entire feature/module. Usage: /focused-fix.
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.
build-fix
A build-error fixing procedure for TypeScript projects. It runs the project build, groups and explains errors, applies fixes one at a time, and checks the build again.
auto-fix
A bug-fixing command that focuses on reproducing a problem and making the smallest suitable code change.
backprop
Trace a bug back to a spec gap and generate regression tests.
sdlc-verify
Phase 3 — Verify. Runs security-engineer always + performance-engineer when needsperformanceaudit is true. Reads build-handoff.md for clean context.