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 gear-foundation/vara-skills --skill gear-message-executiongit clone --depth 1 https://github.com/gear-foundation/vara-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/gear-foundation/vara-skills/gear-message-execution)<a href="https://agentmods.dev/skills/gear-foundation/vara-skills/gear-message-execution"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/gear-message-execution/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/gear-foundation/vara-skills/gear-message-execution"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/gear-message-execution.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 | $0.00062 | $0.00672 |
| Opus 5 | $0.00031 | $0.00336 |
| Sonnet 5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
gear-message-execution 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gear Message Execution
Goal
Provide a focused local path for reasoning about message flow and execution behavior in standard Gear/Vara Sails work.
Inputs
../../references/gear-execution-model.md../../references/gear-sails-production-patterns.md../../references/gear-messaging-and-replies.md../../references/gear-gas-reservations-and-waitlist.md../../references/scale-binary-decoding-guide.md../../references/sails-syscall-mapping.md
Route Here When
- replies, timeouts, or error replies are surprising
- delayed work spans future blocks
- reservations or waitlist behavior affect the design
- a builder is mixing raw payload handling into an otherwise standard Sails flow
- raw hex, reply bytes, event bytes, or metadata-vs-IDL decoding path is unclear
- a reply from a hardcoded non-program
ActorIddoes not decode as a Sails route; route togear-builtin-actorsfor the matchinggbuiltin_*::Responsetype
Working Model
- Confirm what executes now versus after the next block.
- If raw bytes are involved, classify the source first: constructor, service payload, reply, event, full state, or state-function output.
- Determine whether the bytes are Sails-routed, plain SCALE, or metadata-driven state output.
- Match the decoder artifact to the source: generated client or
.idl,ProgramMetadata, orstate.meta.wasm. - Identify whether the path is fire-and-forget, reply-driven, delayed, or reservation-backed.
- Separate transport failure, timeout, and error reply.
- Check whether rollback should revert local state if a send or reply path fails.
- If the path is in tests, confirm the block-advance pattern and expected reply timing.
Guardrails
- Treat reply, timeout, and late hook execution as distinct states.
- Keep staged payload flows paired with their commit step.
- Treat reservation duration and waitlist expiry as architecture constraints.
- Use
exec::gas_available()(orSyscall::gas_available()if using Sails) when checking available gas during the current execution. - Prefer generated Sails clients unless debugging the route or codec layer.
- If a Sails route is involved, expect Sails Header-aware encoding rather than a raw struct payload.
- Keep the guidance on the standard Gear/Vara Sails path.
- Prefer local repo references over external skill dependencies.
- Do not start with plain
Decode::<T>on arbitrary bytes when a Sails route may be involved. - Match decode artifact to source: generated client or
.idlfor standard Sails interface paths,ProgramMetadatafor full state, andstate.meta.wasmfor state-function output. - Treat
gear-metaas a debugging fallback, not the first-choice default path.
What ships with it
3 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.
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 · 54 lines · 62 tokens per session scan A fe356fce521f
gear-message-execution is a skill published in the GitHub repository gear-foundation/vara-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 672 once invoked, about $0.0003 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
code-changes
Orchestration workflow for any task that ends in code changes: issue analysis, pull request review, feature implementation, bug fixes, refactors, or fleshing out an idea. MUST be invoked at the start of such a task, before reading or writing any code. Defines how to analyze first, gate on user approval, plan, pick the…
cross-environment-semantic-drift
L1 trigger - audits L1/L2 boundary bugs, precompile context assumptions, integer width mismatches at environment boundaries, and EVM-on-non-EVM drift.
consensus-math-correctness
L1 trigger - audits consensus arithmetic for truncation, unused bounds, EMA direction, and threshold edge errors.
alchemy-cli
Use the Alchemy CLI (@alchemy/cli) for live blockchain data, transaction lookups, NFT/token/portfolio queries, simulation, tracing/debugging, contract reads/writes, wallet-signed sends, swaps and cross-chain bridges, Solana RPC/DAS plus wallet sends, webhook management, and Alchemy app administration. Preferred…
finish-it
Scope-cutting and shipping discipline from Derek Yu's 'Finishing a Game' and 'Death Loops', jam culture, and veteran shipping practice — diagnose why a game project stalled, cut to a shippable core, define a binary finish line, ship it. Use when: a game project is stalled or sprawling, 'I keep adding features', 'it's…
skmtc-debug
Diagnose failures in SKMTC sessions — no output, wrong output, error messages, bundle freshness, parseIssues, "Registered definition mismatch", ref cycles, "Module not found" in generated code, or any other broken behavior. Applies across both CLI usage and generator authoring contexts. Use this skill when the user…