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/sruja-ai/srujaWrote 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/sruja-ai/sruja/sruja-confidence-report)<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-confidence-report"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-confidence-report/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/sruja-ai/sruja/sruja-confidence-report"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-confidence-report.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 | $0.00000 | $0.00553 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
sruja-confidence-report 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sruja Confidence Report
Generate a post-AI-edit confidence report showing what changed, what evidence was checked, what risks remain, and what to inspect at 3AM.
When to use
After an AI coding assistant (Cursor, Copilot, Claude, etc.) makes changes to your codebase. Run this before reviewing the diff to get a structured overview of verification status.
Workflow
1. AI edits code (in your editor)
2. sruja confidence -r . -f md ← this command
3. Review the report
4. Address blockers if any
5. Merge when confident
Profiles
review(default) — review + intent check + drift checkcoding— lint repo.sruja + build/test + drift checkbugfix— focus on file + build/test + intent check (requires--file)arch— lint + drift + intent + review
Commands
# Default: review profile, markdown output
sruja confidence -r .
# JSON output for tooling
sruja confidence -r . -f json
# Bugfix profile with focus file
sruja confidence --profile bugfix --file src/auth.rs -r .
# With evidence pack
sruja confidence --profile coding --evidence-pack -r .
Report sections
- Verdict — confidence level (high/medium/low) and summary
- What Changed — list of changed files from git diff
- Intent Alignment — intent check results
- Architecture Alignment — drift check results
- Evidence Checked — verification steps that ran
- Human Review Queue — blockers and watch items
- 3AM Notes — first places to check and follow-up commands
Confidence levels
- High — all verification passed, no blockers, intent is clear
- Medium — verification passed but some signals are missing or unclear
- Low — verification failed, drift detected, or intent errors found
Advisory behavior
The command is advisory by default: it exits successfully even if the report contains blockers. It only exits non-zero for fatal execution/input errors (e.g., repo not found).
Integration with existing workflow
# Before AI edits (optional)
sruja focus --file src/auth.rs -r .
# AI edits happen here...
# After AI edits
sruja confidence -r . -f md
# If blockers found, investigate
sruja drift -r . -f json
sruja intent check -r . -f 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.
- 12d ago First seen · 77 lines · 0 tokens per session scan A 27d090168475
sruja-confidence-report is a command published in the GitHub repository sruja-ai/sruja (24 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 553 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 2026-08-30.
Other commands, from other repositories
check
Fail on NET-NEW architecture violations only — the same ratchet ArchSteer runs in CI, run right now.
clean
Clean AI-generated slop from code.
debt
Scan codebase for technical debt and produce a prioritized report.
refactor
Safe code refactoring: change structure without changing behavior.
spec-review
Run a specification review on the given code or document.
sdd-apply
Implement SDD tasks — writes code following specs and design.