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 bdfinst/agentic-dev-team --skill human-oversight-protocolgit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/human-oversight-protocol)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/human-oversight-protocol"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/human-oversight-protocol/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/bdfinst/agentic-dev-team/human-oversight-protocol"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/human-oversight-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 167 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 169 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00050 | $0.02705 |
| Opus 5.5 | $0.00020 | $0.01082 |
| Sonnet 5.5 | $0.00010 | $0.00541 |
| Haiku 4.5 | $0.00005 | $0.00270 |
Grade A, and why
human-oversight-protocol 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 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.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Oversight Protocol
Constraints
- Approval gates cannot be skipped; do not proceed past a gate without explicit human sign-off.
- Ethical concerns are never auto-resolved; always escalate.
- Intervention commands (
override,pause,stop) take immediate effect with no debate. - Overrides accumulate; 3+ overrides on the same topic must trigger a config amend.
Plan Review as Primary Quality Gate
The implementation plan is the primary review artifact, not the code. Traditional line-by-line code review is replaced by plan review for AI-generated work — 200 lines of plan is far more reviewable than 2,000 lines of generated code, and if the plan is correct and tests pass, the code is trustworthy.
Plan review checklist
- Does the research accurately describe how the system works? (File paths, data flows, dependencies)
- Does the plan address the right problem?
- Are the specified changes complete — no missing files or edge cases?
- Is the test strategy sufficient to verify correctness?
- Are there architectural concerns the plan missed?
When to still review code
- Security-sensitive paths (authentication, authorization, crypto)
- Performance-critical paths
- When tests are insufficient to verify correctness
- When the plan was ambiguous about implementation details
Approval Gates
Gate classification
Every agent action falls into one of three categories:
| Category | Description | Human involvement |
|---|---|---|
| Autonomous | Routine work within agent's defined scope | None — deliver output directly |
| Notify | Significant but within scope; human should be aware | Deliver output + flag what was decided and why |
| Approve | Outside routine scope or high-impact; human must sign off | Present proposal, wait for explicit approval |
Standard approval gates
These actions always require human approval. Every gate below writes an
approval entry to .claude/metrics/config-changelog.jsonl per the Audit trail
schema — proposed, evidence_shown, and risks_surfaced included.
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 · 225 lines · 50 tokens per session scan A d95442ae4e01
human-oversight-protocol is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 2,705 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.