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 skills add VandanaAjayDubey111/great-pm --skill responsible-ai-guardrailsgit clone --depth 1 https://github.com/VandanaAjayDubey111/great-pmWrote 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/skills/vandanaajaydubey111/great-pm/responsible-ai-guardrails)<a href="https://agentmods.dev/skills/vandanaajaydubey111/great-pm/responsible-ai-guardrails"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/responsible-ai-guardrails/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/skills/vandanaajaydubey111/great-pm/responsible-ai-guardrails"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/responsible-ai-guardrails.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 | $0.00108 | $0.03799 |
| Opus 5.5 | $0.00043 | $0.01520 |
| Sonnet 5.5 | $0.00022 | $0.00760 |
| Haiku 4.5 | $0.00011 | $0.00380 |
Grade B, and why
responsible-ai-guardrails scanned grade B with 1 finding 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 1mo 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
| **Jailbreak / injection** | Can input or retrieved text override the system prompt or policy? | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex host binding
- Treat references to Claude slash workflows as the equivalently named Codex skill.
- Before delegating to any specialist, read the
great-pm-runtimeskill and the selected packaged role file. - Treat "invoke", "assign", "delegate", "spawn", and source Agent-tool instructions as a required Codex
spawn_agentcall with that role and a bounded assignment. - For the spawn tool's
task_nameoragent_nameidentifier, replace canonical role-name hyphens with underscores (query-refiner-pm→query_refiner_pm). Keep canonical names unchanged in prompts, filenames, verdict logs, and user-facing output; this is an internal identifier mapping, not a role rename. - Store every returned agent identifier. Never call a wait tool until a spawn has returned an identifier, and wait only on identifiers returned by successful spawns.
- If
spawn_agentis unavailable or a spawn fails, report BLOCKED; do not impersonate the specialist or wait on an empty agent set. - Resolve bundled paths from the installed GreatPM plugin root.
- Ignore Claude-only model aliases, colors, turn limits, and tool allowlists.
- Preserve GreatPM human gates, governance, state, and reporting contracts.
Responsible AI guardrails — the PM-owned safety gate
A pre-launch model review is not enough. The teams that ship AI safely treat safety as a property of the running product, integrated into the development lifecycle with a feedback loop that connects risk-testing directly to product and policy decisions. This is the recurring PM dilemma stated honestly: ship this quarter, or invest in evals + red-teaming + runtime guardrails first? This skill exists to make that a deliberate, documented decision rather than a default.
Crucially, this is product-craft safety, not legal compliance.
ai-regulation, india-fintech, and us-fintech cover the regulatory
and legal obligations. This skill covers the engineering of safety —
the guardrails, thresholds, red-team scenarios, and disclosures a PM owns
regardless of what the law requires. It is also distinct from ai-evals:
evals measure quality; this manages safety and risk.
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.
- 1mo ago First seen · 284 lines · 108 tokens per session scan B 3a28b1e221eb
responsible-ai-guardrails is a skill published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 3,799 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.
Other skills, from other repositories
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
weknora-rag-search
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
execution-orchestrator
A planning and coordination skill for substantial coding tasks. It chooses how work should be organized, tracked, delegated, reviewed, and resumed across execution steps.
nexus-configuration
A skill for reading, planning, approving, and checking configuration in Nexus, the current private conversation or room. It covers settings such as agents, rooms, providers, channels, connectors, skills, models, tools, and MCP connections.