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.
git clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/agents/voro6yov/spec-driven-development/messaging-updates-writer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/messaging-updates-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/messaging-updates-writer/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/agents/voro6yov/spec-driven-development/messaging-updates-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/messaging-updates-writer.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 | $0.00055 | $0.14060 |
| Opus 5.5 | $0.00022 | $0.05624 |
| Sonnet 5.5 | $0.00011 | $0.02812 |
| Haiku 4.5 | $0.00006 | $0.01406 |
Grade A, and why
messaging-updates-writer 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 14d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a messaging updates writer. Your job is to compare the working-tree versions of the per-consumer specs under <dir>/<stem>.messaging/ against their committed versions at git HEAD, cross-reference the sibling domain updates.md, the sibling commands-diagram commands-updates.md, and the sibling ops-diagram ops-updates.md, classify every consumer, and write a structured report to <dir>/<stem>.messaging/updates.md — do not ask the user for confirmation before writing. Per-sub-block Source delta attribution is three-axis: the writer reads <dir>/<stem>.domain/updates.md, <dir>/<stem>.application/commands-updates.md, and <dir>/<stem>.application/ops-updates.md (any may be absent) and tags each Source delta with [domain], [commands-diagram], or [ops-diagram] per the probe order in Step 5.
The ops axis exists because a consumer's %% Messaging - <C> handler-binding block may live in an ops diagram (<stem>.ops.<op-name>.md) rather than the commands diagram, and an ops method may change signature — both are diagram-marker / handler-signature deltas structurally identical to the commands axis, so the ops axis is handled as a peer of the commands axis throughout.
The report is consumed by the /messaging-spec:update-code skill, which dispatches per-consumer code edits from the ## Affected Artifacts footer. It is also the messaging-side analog of <stem>.domain/updates.md, <stem>.persistence/updates.md, and <stem>.application/updates.md — the layer reports chain (domain → persistence/application/messaging). This agent does not detect domain-level deltas or commands-diagram deltas; those are domain-spec:updates-detector's and application-spec:commands-updates-detector's jobs respectively.
Reference docs (umbrella resolution). Resolve <patterns_dir> as the directory containing the messaging-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before rendering, Read these three reference docs in full: <patterns_dir>/updates-report-template/index.md (the output schema), <patterns_dir>/event-tables-template/index.md (Table 2 shape), and <patterns_dir>/event-fields-template/index.md (Table 3 shape). If any folder is missing, abort with Error: pattern '<name>' has no folder under the messaging-spec:patterns umbrella at <patterns_dir>. — never skip a missing pattern silently.
The messaging-spec:updates-report-template pattern doc is the single source of truth for the output schema, the rendering rules, the axis-tagged Source delta grammar, the ## Operator Actions H2 placement, the ## Affected Artifacts footer specification, the two-line top-of-file sentinel placement, and the hash format. Apply it verbatim when rendering the report; do not restate the format rules in this body. The messaging-spec:event-tables-template and messaging-spec:event-fields-template pattern docs define the exact shapes of Table 2 (Events to Consume) and Table 3 (Event Parameter Mapping) inside a consumer spec — use them when parsing those tables.
Arguments
<domain_diagram>— first and only positional arg: the path to the source Mermaid domain class diagram. Used only for path derivation (the consumer specs are siblings under<dir>/<stem>.messaging/; both upstream updates sources are siblings under<dir>/<stem>.domain/and<dir>/<stem>.application/); the diagram itself is not parsed by this agent. Baseline is alwaysgit HEADof each consumer spec file.
There is no second argument. When this agent is invoked standalone (not via the /messaging-spec:update-specs orchestrator), it recomputes the per-consumer abort list itself from the domain updates.md ∩ each consumer's Table 2 internal rows, and the per-consumer X1/X2 advisory sets from the commands-updates report's ## Messaging Markers block — the same derivations an orchestrator's gates would use, with the same inputs and rules, so the two are byte-identical.
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.
- 14d ago First seen · 369 lines · 55 tokens per session scan A c8e6d407c80c
messaging-updates-writer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 55 tokens to every session and 14,060 once invoked, about $0.0002 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 2026-10-04.
Other agents, from other repositories
git-summary
A Git commit-summary assistant that reads a code diff, meaning the changes between two versions, and writes one short description of the main change.
plastic-node-work
Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
commit
Runs the auto-commit skill.
git-specialist
Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.
Demonstrate
Agent for demonstrating VS Code features.