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-verify-task)<a href="https://agentmods.dev/commands/sruja-ai/sruja/sruja-verify-task"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-verify-task/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-verify-task"><img src="https://agentmods.dev/badge/commands/sruja-ai/sruja/sruja-verify-task.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-verify-task 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 9d 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.
What it actually says
Sruja: Verify task
Run verification steps for a task profile. Use before marking a task as done.
Related: plan-feature → implement-from-plan → verify-task → reflect-on-run
Usage
# Default: coding profile
sruja verify-task --profile coding -r .
# Bugfix targeting a specific file
sruja verify-task --profile bugfix --file <path> -r .
# Pre-merge review
sruja verify-task --profile review -r .
# Architecture change
sruja verify-task --profile arch -r .
# JSON output for CI/MCP
sruja verify-task --profile coding -r . -f json
Steps
-
Choose the right profile based on the task type:
coding— New features, refactors (default)bugfix— Bug fixes (use--fileto target)review— Pre-merge reviewarch— Architecture/DSL changes
-
Run verification:
sruja verify-task --profile <profile> -r . -
If all passed: Task is verified. Optionally record an affirmation learning.
-
If any failed:
- Review the failed step output
- Fix the issue
- Re-run verify-task
- Record a correction learning:
sruja agent record -r . \ -c "<task context>" \ -H "<what was tried>" \ -o failed \ -g "<correction for next time>"
Profiles
| Profile | Steps |
|---|---|
coding |
lint repo.sruja + just check (or make check) + drift |
bugfix |
focus --file + just check (or make check) + intent check |
review |
review -f json + intent check + drift |
arch |
lint repo.sruja + drift + intent check + review |
References
- docs/HOST_AGENT_INTEGRATION.md — Integration contract
- AGENTS.md — Build commands
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.
- 9d ago First seen · 67 lines · 0 tokens per session scan A 54eedd70eedf
sruja-verify-task is a command published in the GitHub repository sruja-ai/sruja (23 stars, last pushed yesterday), 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
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
ng-red-team
Portable command prompt generated from skills/stress-testing-agent-changes/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
generate-tests
Generate comprehensive tests for specified code.
fire-verify-uat
Conversational User Acceptance Testing with automatic parallel diagnosis on failures.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.