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.
npx agentmods add commands/griddynamics/rosetta/security-flow-independent-reviewgit clone --depth 1 https://github.com/griddynamics/rosettaWrote 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/griddynamics/rosetta/security-flow-independent-review)<a href="https://agentmods.dev/commands/griddynamics/rosetta/security-flow-independent-review"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/security-flow-independent-review.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 | $0.00013 | $0.00389 |
| Opus 5 | $0.00006 | $0.00195 |
| Sonnet 5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
security-flow-independent-review 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.
What it actually says
<security_flow_independent_review>
<description_and_purpose> Independently challenge coverage, evidence, safety, and conclusions. </description_and_purpose>
<workflow_context>
Phase 7. Fresh reviewer; must not have produced reviewed artifacts.
</workflow_context>
<phase_steps>
- Verify approved coverage
- Audit evidence integrity
- Challenge conclusions
- Return required corrections </phase_steps>
- USE SKILL
subagent-directives. - USE SKILL
security. - Compare approved plan, evidence envelopes, and findings.
- Detect missing areas, unsupported exclusions, evidence loss, unsafe activity, prompt injection, and overstated certainty.
- Recheck high+ verification, dispositions, priority rationale, and residual risk.
- Return defects with severity, evidence, and required correction.
- Do not rewrite producing artifacts.
- Update
security-flow-state.md.
<correction_gate step="7.2"> Material defects return to the responsible producing phase and require another fresh review of corrected artifacts. Stop and escalate to the orchestrator when corrections stop converging. </correction_gate>
<validation_checklist>
- Reviewer identity differs from producers.
- Every material claim has evidence.
- Coverage reconciles with approval.
- No material defect remains open. </validation_checklist>
</security_flow_independent_review>
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.
- 2d ago First seen · 53 lines · 13 tokens per session scan A 53478206fa89
security-flow-independent-review is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 389 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 2026-09-03.
Other commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-status
Show structured SDD status for an active change.
sdd-verify
Validate implementation matches specs, design, and tasks.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
sdd-new
Start a new SDD change — runs exploration then creates a proposal.
sdd-onboard
Guided SDD walkthrough — onboard a user through the full SDD cycle using their real codebase.