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 harness/harness-skills --skill approve-exemptgit clone --depth 1 https://github.com/harness/harness-skillsWrote 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/harness/harness-skills/approve-exempt)<a href="https://agentmods.dev/skills/harness/harness-skills/approve-exempt"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/approve-exempt/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/harness/harness-skills/approve-exempt"><img src="https://agentmods.dev/badge/skills/harness/harness-skills/approve-exempt.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 264 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 47 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 | $0.00168 | $0.05951 |
| Opus 5 | $0.00084 | $0.02975 |
| Sonnet 5 | $0.00034 | $0.01190 |
| Haiku 4.5 | $0.00017 | $0.00595 |
Grade A, and why
approve-exempt 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- approve-exempt — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approve Exemption
Approve one or more Pending STO security exemptions. This skill covers the approval
workflow after someone has requested an exemption (see /exempt-vuln for creation).
Pending scope is only PROJECT, PIPELINE, or TARGET. Exemptions are requested at
project, pipeline, or target scope only (All Issues → project; Vulnerabilities tab → project,
pipeline, or target). STO does not create pending requests at org or account scope — those
wider scopes exist only after elevation on approve (body.scope ORG or ACCOUNT). You
will not see scope: ORG or scope: ACCOUNT on rows from status: Pending in normal flows.
If a list row shows ORG/ACCOUNT, it is already approved/widened (re-approve or a different
workflow), not a fresh pending request this skill targets.
Harness exposes two different "scope" ideas — do not mix them up:
| Concept | What it controls | How you use it |
|---|---|---|
| Listing scope | Which project's exemption queue you read | Always list at project scope. Never pass resource_scope='account' or 'org' to harness_list. |
| Approval scope | Where the exemption becomes effective after approval | Passed as body.scope on harness_execute — CURRENT, PROJECT, ORG, or ACCOUNT. |
Users almost always say approve, even when they want org- or account-wide coverage. Treat
"approve for org", "org-wide", and "at account level" as approve with elevation — the MCP
server routes those to the promote endpoint internally. You never need a separate
action='promote' call; always use action='approve' with the right body.scope.
Keep the Harness UI out of the loop. Do not ask the user to copy issue titles, CVEs, or
exemption IDs from the platform. Your default opening move is to list pending exemptions in
chat, show a numbered table, report total, and let them pick by row number (or narrow with
search if they volunteer a keyword). Pagination surfaces more rows on request — you never dump
the full queue at once.
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.
- 11d ago First seen · 432 lines · 168 tokens per session scan A 3ad2b844f6c6
approve-exempt is a skill published in the GitHub repository harness/harness-skills (105 stars, last pushed yesterday), licensed Apache-2.0. It adds 168 tokens to every session and 5,951 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.