dry-run

dry-run is a skill for Claude Code from dynos-fit/dynos-work. It costs 59 tokens per session (1,694 once invoked), scanned A, original, MIT.

A manually triggered check for whether the contract files in a skills pipeline fit together. It verifies that each stage produces the information the next stage requires.

In plain words
What is it for?
Use it to validate the chain from start through plan, execute, audit, and learn when you explicitly run the dry-run command.
Why use it?
It finds missing or incompatible handoffs between pipeline stages before they cause failures.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dynos-work plugin — 33 skills, 37 agents shipped together

Good fit Use it to validate the chain from start through plan, execute, audit, and learn when you explicitly run the dry-run command.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dynos-fit/dynos-work
Claude Code
/plugin install dynos-work

Made for: Claude Code.

Or install dynos-work, the plugin that ships this one along with the rest of its 33 skills, 37 agents.

Wrote 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.

agentmods badge for dry-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/dynos-fit/dynos-work/dry-run/github.svg)](https://agentmods.dev/skills/dynos-fit/dynos-work/dry-run)
Your own site
<a href="https://agentmods.dev/skills/dynos-fit/dynos-work/dry-run"><img src="https://agentmods.dev/badge/skills/dynos-fit/dynos-work/dry-run/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.

agentmods 80×15 button for dry-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/dynos-fit/dynos-work/dry-run"><img src="https://agentmods.dev/badge/skills/dynos-fit/dynos-work/dry-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01694
Opus 5 $0.00030 $0.00847
Sonnet 5 $0.00012 $0.00339
Haiku 4.5 $0.00006 $0.00169

Measured 8d ago against content hash 3af50f1ce9b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dry-run 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 8d 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.

skills/dry-run/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dynos-work: Dry Run

Validate that the contract.json files across all skills form a valid pipeline chain. This skill reads every skills/*/contract.json, determines the pipeline order, and verifies that each stage's outputs satisfy the next stage's required inputs.

Ruthlessness Standard

  • Treat missing or incompatible contract fields as real pipeline breakage, not paperwork.
  • Do not infer compatibility from naming similarity alone.
  • If a downstream stage depends on behavior the upstream contract does not guarantee, call it broken.

What you do

Step 1 -- Discover contracts

  1. Scan all directories under skills/ in the project root.
  2. For each directory, check if a contract.json file exists.
  3. If any skill directory lacks a contract.json, emit a warning that names every specific directory:
    WARNING: Missing contract.json in: skills/foo/, skills/bar/
    
  4. Parse each discovered contract.json file. If any file contains invalid JSON, report it as an error and skip that contract.

Step 2 -- Determine pipeline order

The linear pipeline chain is fixed:

start -> plan -> execute -> audit -> learn

Skills that are NOT part of the linear pipeline (utility skills) are:

  • status
  • investigate
  • resume
  • repair
  • execution
  • dashboard
  • dry-run

Utility skills have contracts but do not participate in linear chain validation. They should still be loaded and listed in the report.

Step 3 -- Validate chain links

For each consecutive pair in the pipeline (stage N -> stage N+1):

  1. Read the output_schema of stage N.
  2. Read the input_schema of stage N+1.
  3. For every field in stage N+1's input_schema where required is true:
    • Check if a field with a matching key exists in stage N's output_schema.
    • If the field exists, check that the type values are compatible (exact match or both resolve to the same base type).
    • If the field is missing from stage N's output_schema, record a FAIL with details.
    • If the field exists but the type does not match, record a FAIL with details.
  4. For optional fields (where required is false), check availability but only emit an INFO-level note if missing, not a FAIL.

Read the full file on GitHub · 178 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 8d ago First seen · 178 lines · 59 tokens per session scan A 3af50f1ce9b3

Subscribe to this mod's changes

dry-run is a skill published in the GitHub repository dynos-fit/dynos-work (2 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,694 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 2026-08-31.

Related

Other skills, from other repositories

ring:migrating-to-lib-observability

Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…

LerianStudio/ring · 104 tokens

ring:using-lib-streaming

Using lib-streaming, Lerian's producer-only event publication library (Kafka/SQS/RabbitMQ/EventBridge), in two modes. Sweep Mode detects DIY publishers (franz-go, sarama, amqp091, watermill, raw AWS SDK) and re-rolled manifests/breakers. Reference Mode catalogs the Builder/Emitter/Catalog facade. Companion to…

LerianStudio/ring · 99 tokens

ring:using-lib-systemplane

Using lib-systemplane, the hot-reload runtime-config plane (Postgres LISTEN/NOTIFY or MongoDB change streams), in two modes. Sweep Mode detects DIY config reload (SIGHUP, fsnotify, viper, pgx LISTEN), manual tenant-scoping, hand-built admin CRUD, and v4 residue. Reference Mode catalogs client lifecycle and…

LerianStudio/ring · 106 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:using-lib-observability

Using lib-observability v1.1.0, Lerian's OpenTelemetry foundation (lib-commons, lib-systemplane, lib-streaming depend on it), in two modes. Sweep Mode detects DIY zap/slog logging, raw OTel metrics, hand-rolled redaction, and hard-coded attribute strings. Reference Mode catalogs the log, metrics, zap, redaction, and…

LerianStudio/ring · 102 tokens

ring:using-outbox

Using the transactional-outbox pattern across lib-streaming (writer) and lib-commons/v5/commons/outbox (repository + relay), in two modes. Sweep Mode detects DIY outbox tables, hand-rolled relay loops, send-and-pray emits, missing WithOutboxTx wrapping, and broker calls inside DB transactions. Reference Mode catalogs…

LerianStudio/ring · 98 tokens