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 agentmods add commands/firstintent/a2a-bridge/initgit clone --depth 1 https://github.com/firstintent/a2a-bridgeWhat 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 | $0.00015 | $0.00539 |
| Opus 5 | $0.00008 | $0.00269 |
| Sonnet 5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
init 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 yesterday.
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.
What it actually says
Bootstrap or update A2aBridge's project-local configuration in this workspace.
Follow these rules:
- Work only inside
.a2a-bridge/. - Do not install plugins or modify
.claude/settings.jsonhere. Plugin setup belongs to terminal workflows:a2a-bridge initattempts best-effort plugin installation, anda2a-bridge devhandles local marketplace registration/sync. - Preserve user edits when the files already exist. Update only the fields the user asked to change.
- Keep
.a2a-bridge/config.jsonvalid JSON. - Keep
.a2a-bridge/collaboration.mdhuman-editable and concise.
If .a2a-bridge/config.json is missing, create it with this default template:
{
"version": "1.0",
"daemon": {
"port": 4510,
"proxyPort": 4511
},
"agents": {
"claude": {
"role": "Reviewer, Planner",
"mode": "push"
},
"codex": {
"role": "Implementer, Executor"
}
},
"markers": ["IMPORTANT", "STATUS", "FYI"],
"turnCoordination": {
"attentionWindowSeconds": 15,
"busyGuard": true
},
"idleShutdownSeconds": 30
}
If .a2a-bridge/collaboration.md is missing, create it with this default template:
# Collaboration Rules
## Roles
- Claude: Reviewer, Planner, Hypothesis Challenger
- Codex: Implementer, Executor, Reproducer/Verifier
## Thinking Patterns
- Analytical/review tasks: Independent Analysis & Convergence
- Implementation tasks: Architect -> Builder -> Critic
- Debugging tasks: Hypothesis -> Experiment -> Interpretation
## Communication
- Use explicit phrases: "My independent view is:", "I agree on:", "I disagree on:", and "Current consensus:"
- Tag messages with [IMPORTANT], [STATUS], or [FYI]
## Review Process
- Cross-review: author never reviews their own code
- All changes go through feature/fix branches + PR
- Merge via squash merge
## Custom Rules
<!-- Add project-specific collaboration rules here -->
When you finish, briefly summarize what changed and point the user to the two files you updated.
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.
- yesterday First seen · 71 lines · 15 tokens per session scan A 3ce7de3320f9
init is a command published in the GitHub repository firstintent/a2a-bridge (8 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 539 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
greet
Say hello to the user and offer to summarize a note.
do
End-to-end task execution — research, plan, implement, review, and merge via PR.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
workflow
Orchestrate multi-step workflows with durable subtask waits and parent wake delivery.