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 phenomenoner/Chatgpt-Codex-App-Plus --skill operate-a2a-superhubgit clone --depth 1 https://github.com/phenomenoner/Chatgpt-Codex-App-PlusWrote 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/phenomenoner/chatgpt-codex-app-plus/operate-a2a-superhub)<a href="https://agentmods.dev/skills/phenomenoner/chatgpt-codex-app-plus/operate-a2a-superhub"><img src="https://agentmods.dev/badge/skills/phenomenoner/chatgpt-codex-app-plus/operate-a2a-superhub/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/phenomenoner/chatgpt-codex-app-plus/operate-a2a-superhub"><img src="https://agentmods.dev/badge/skills/phenomenoner/chatgpt-codex-app-plus/operate-a2a-superhub.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 | $0.00132 | $0.01510 |
| Opus 5.5 | $0.00053 | $0.00604 |
| Sonnet 5.5 | $0.00026 | $0.00302 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
operate-a2a-superhub 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate A2A Superhub
Preflight
- Resolve the exact target. Default only to an explicit loopback target; never guess a remote URL.
- Read health, readiness, version, Agent Card, structured capabilities,
artifact size limit, and derivation state through surfaces the server
actually advertises. Prefer
/v2/capabilitiesand verifydeliveryModel: logical.v2,wakeupAckMode: none,ackCursorSource: inbox-only, and lifecycle availability before using those features. - Compare the server surface with references/compatibility.json. Treat
implemented: falseand absent capabilities as unavailable. - Resolve the authenticated subject and scopes without printing or copying token material.
- Report the negotiated memory contract, degraded reasons, and source/index revisions before choosing a workflow. V1 deliveries are per-reason rows through version 0.3.x, not v2 logical delivery identities.
If discovery is ambiguous, perform read-only discovery only. Stop clearly on an unsupported version, missing capability, or missing authority; do not probe by mutation.
Run scripts/doctor.py --json for a read-only preflight and negotiated
transport choice. It tries the packaged MCP stdio sidecar, uses subscriptions
when advertised, falls back to polling when they are absent, and distinguishes
connection, authentication, and compatibility failures without printing the
token. Use --transport http to require HTTP or --transport mcp to fail
closed unless MCP initializes. Run scripts/smoke.py --json against disposable state by default. An
existing target requires both --url and --allow-write plus sender/receiver
token environment handles.
For an approved new loopback deployment, scripts/bootstrap_local.py creates a
private principal registry plus separate agent/operator connection profiles and
refuses to overwrite credentials. It never prints bearer tokens.
scripts/launch_mcp.py reads one private profile, verifies that the hub
authenticates the expected subject with the current memory surface, and only
then starts the MCP stdio sidecar. Read
the local connection workflow
before using either script.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 225 B
- references/capabilities-and-versions.md 5.1 KB
- references/compatibility.json 1.2 KB
- references/security-and-approval.md 4.0 KB
- references/troubleshooting.md 3.6 KB
- references/workflows.md 14 KB
- scripts/bootstrap_local.py 6.5 KB runs code
- scripts/doctor.py 4.5 KB runs code
- scripts/launch_mcp.py 5.4 KB runs code
- scripts/smoke.py 4.9 KB runs code
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 · 116 lines · 132 tokens per session scan A 38ffd3df1cde
operate-a2a-superhub is a skill published in the GitHub repository phenomenoner/Chatgpt-Codex-App-Plus (2 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 1,510 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
challenge-resolve
Independently review and fix a bounded task through convergence rounds, with evidence-backed closure and explicit stop/remediation decisions. Use only when the user explicitly requests an adversarial review-and-fix loop over an existing implementation, feature, problem, or diff; not for ordinary review (code-review)…
code-remediate
Collect and resolve selected findings in one pass, then verify; bare PR targets use online items, while PR +review authorizes matching review evidence and any needed review step.
codegraph
Use for repo structure, symbol navigation, dependency analysis, duplicate triage, and PR impact review when plain text search is too shallow.
checking-code-quality
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
morpheus
Second opinion and final verdict for engineering decisions. Challenges a plan, design, PR, claim, fix, or bug theory with cited evidence, steelmans the user's position first, asks when an assumption would flip the verdict, labels how each claim is known, and always lands on a verdict or a recommended option with…