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 agents/pome223/missionos/dispatch-idempotencygit clone --depth 1 https://github.com/pome223/missionosWhat 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 | $0.00000 | $0.01199 |
| Opus 5 | $0.00000 | $0.00600 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
dispatch-idempotency 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 2d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatch Idempotency Contract
This contract defines the MissionOS dispatch_ref baseline that must be used
before an ADK workflow can approach an external execution boundary. It does not
give ADK, an LLM, or a completed graph node approval or dispatch authority.
Identity and Request Binding
One dispatch_ref identifies one bounded external send identity. MissionOS
binds it to the SHA-256 of the canonical request payload before sender
invocation.
- the same
dispatch_refand the same request hash may return an existing receipt, but may not send again - the same
dispatch_refwith a different request hash fails closed asdispatch_ref_payload_mismatch - a changed action, target, parameter envelope, or Recovery proposal requires a
new bounded action, approval, and
dispatch_ref - ADK event IDs and node IDs are correlation fields only; they are not the idempotency identity
The durable implementation is DispatchAuthorityTable in
src/gateway/missionos_dispatch_runtime.py. Authority-token consumption and
dispatch idempotency are separate checks. Passing one does not imply passing
the other.
Required Sender Sequence
An execution boundary must use this order:
- Reload and validate the canonical MissionOS approval, bounded action, deterministic gate, fresh telemetry, backend descriptors, and prior receipts.
- Call
claim_dispatch_ref()with the stabledispatch_refand complete canonical request payload. - Stop if
send_permitted=false. - If
idempotency_status=existing_receipt, return the recorded receipt without invoking the sender. - If
idempotency_status=unknown_send_outcome, stop for explicit receipt or external-state reconciliation. Do not retry automatically. - Immediately before invoking the external sender, call
mark_dispatch_send_started(). Invoke the sender only when this call returnssend_permitted=true. - Record the sender return with
record_dispatch_receipt(). - Record ACK, observed effect, verifier verdict, and completion in their own canonical evidence stages.
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.
- 2d ago First seen · 127 lines · 0 tokens per session scan A 5413b5632fcf
dispatch-idempotency is an agent published in the GitHub repository pome223/missionos (2 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,199 tokens. 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 agents, from other repositories
Anti-Vibe Writing Dev
Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
review-e2e
E2Eテストの健全性と整合性を総合レビュー。goto制限、モック禁止、ユーザーフロー再現性、DI適切性、レコード変化アサーション、待機戦略を検証。.
PersonaActor
Fully impersonate one Agentweaver persona and drive the real target API one live turn at a time via direct curl calls against the live OpenAPI spec — deciding each next action from actual API responses, never a pre-written script. Returns the resulting transcript to Harness.
Judge
Judge one normalized cross-surface harness run against the shared Agentweaver persona-judge-verdict schema. Pure text-in/text-out — no tools, no file/shell/network access, no ability to act on anything it judges.
speckit.squad.status
Show alignment between your spec, tasks, and Squad agents.
speckit.squad.generate
Re-generate Squad agent definitions as your plan evolves.