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/sairam0424/MindForgeWrote 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/sairam0424/mindforge/ai-safety)<a href="https://agentmods.dev/commands/sairam0424/mindforge/ai-safety"><img src="https://agentmods.dev/badge/commands/sairam0424/mindforge/ai-safety.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 | $0.00043 | $0.00523 |
| Opus 5 | $0.00022 | $0.00262 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
mindforge:ai-safety 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 4d 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
<execution_context> @.mindforge/skills/ai-safety-alignment/SKILL.md </execution_context>
-
Input Validation Layer: Design prompt injection detection using classifier models and pattern matching, implement adversarial input filtering with anomaly detection, and create user intent verification for high-risk operations.
-
Output Safety Controls: Architect content moderation pipeline with toxicity classifiers (Perspective API, OpenAI Moderation), implement fact-checking and hallucination detection for critical domains, and design PII redaction with entity recognition and regex patterns.
-
Alignment Mechanisms: Define constitutional AI principles and values hierarchy, implement preference learning from human feedback (RLHF/RLAIF), and design reward modeling for behavior shaping toward safe outcomes.
-
Monitoring and Observability: Create real-time dashboards tracking safety metric distributions (toxicity scores, rejection rates), implement anomaly alerting for policy violations, and design audit logging for compliance and forensics.
-
Intervention Protocols: Design human-in-the-loop workflows for uncertain cases, implement circuit breakers with automatic system degradation, and create escalation paths for critical safety incidents.
-
Continuous Improvement: Establish red-teaming protocols for adversarial testing, design A/B testing framework for safety mechanism refinement, and implement feedback loops from user reports and moderator reviews.
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.
- 4d ago First seen · 38 lines · 43 tokens per session scan A ad0e5202c80c
mindforge:ai-safety is a command published in the GitHub repository sairam0424/MindForge (0 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 523 once invoked, about $0.0002 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
gate-p6-security
Evaluates all security-relevant points of the Gate-P6 checklist and grants Security approval.
golden-path
The golden path. One command, idea to merged PR. Runs the full pipeline, prd → prp → plan → dev → test → pr, with sensor + eval gates at every stage.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.