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 znlgis/my-opencode-deepseek-config --skill gh-cligit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/gh-cli)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/gh-cli"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/gh-cli/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/znlgis/my-opencode-deepseek-config/gh-cli"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/gh-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 154 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00088 | $0.05672 |
| Opus 5.5 | $0.00035 | $0.02269 |
| Sonnet 5.5 | $0.00018 | $0.01134 |
| Haiku 4.5 | $0.00009 | $0.00567 |
Grade A, and why
gh-cli scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
based on [cli/cli](https://github.com/cli/cli) trunk. Prefer `gh` over raw `curl` How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI (gh) agent patterns
Authoritative patterns for driving the official gh CLI (v2.100.0) from agents,
based on cli/cli trunk. Prefer gh over raw curl
or gh api — gh handles auth, pagination, and JSON output automatically.
Security Advisory — escape-sequence injection (v2.97.0)
v2.97.0 fixed 4 escape-sequence injection vulnerabilities. These commands can inject ANSI control sequences (cursor movement, screen clearing, clipboard exfiltration) when output is rendered to a terminal:
| Affected command | Risk |
|---|---|
gh gist view |
Untrusted gist content → terminal |
gh api |
Untrusted API response → terminal |
gh pr diff |
Untrusted PR content → terminal |
gh release download --output - |
Untrusted release artifact → stdout/terminal |
gh codespace logs |
Untrusted container output → terminal |
gh agent-task view / create |
Untrusted task description/output → terminal |
Agent rules:
- Never pipe output to a terminal renderer — prefer
--json, use> filefor raw content; nevergh release download --output -(stdout), always--output <path>. - For
gh repo read-file, binary content is auto-refused and ANSI is stripped by default since v2.97; use--allow-escape-sequencesonly when you need raw escapes and understand the risk. - When fetching issues/PRs/comments from untrusted repos, prefer
--jsonover human-readable output — JSON is not vulnerable to escape injection.
Other v2.96.0 / v2.97.0 fixes (advisory → impact → rule):
| Advisory | Impact | Agent rule |
|---|---|---|
| GHSA-cg6r-mpgc-h9mm | gh auth status (without --show-token) prints a token fragment for github_pat_* / ghs_* / ghu_* and the Actions GITHUB_TOKEN; classic gho_* / ghp_* are unaffected. |
Upgrade ≥2.97.0; redact the token line before sharing output; never ship this output to CI logs. |
| GHSA-mm27-mwq9-fr5g | gh attestation verify --signer-repo/--signer-workflow interpolates the value into a regex without escaping metacharacters (. matches any char), so a lookalike name can satisfy a matcher intended for a trusted signer. |
Only safe on ≥2.97.0; else use --repo/--owner (exact string match) or manually verify the SAN. |
| GHSA-4fjg-2h4q-fwg3 | Some REST request URLs built without escaping variable path segments → path traversal; a crafted name redirects gh to a different resource than intended. |
Upgrade 2.97.0; be cautious with untrusted repo/input names. |
| GHSA-8cg3-r6g9-fpg2 | gh codespace jupyter opens the codespace-supplied URL unvalidated; a malicious codespace returns a vscode:// link → command execution on the host (variant of GHSA-p2h2-3vg9-4p87 / CVE-2024-52308). |
Upgrade ≥2.96.0; only use trusted codespaces. |
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.
- 5d ago Changed · +26 lines acb369a8bcc1
- 14d ago Changed · +1 lines 6725e8845bd7
- 1mo ago Changed · +42 lines e821c92e2613
- 1mo ago Changed · +2 lines 704132750fe1
- 1mo ago Changed · +9 lines f13b9acbf997
- 1mo ago First seen · 318 lines · 88 tokens per session scan A c8b87b80a8f3
gh-cli is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (59 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 5,672 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
final-release-review
Plan, implement, or review final release review work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests final release review work.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
update-v8-version
Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.