constatar-run

constatar-run is a command for Claude Code from JairoTorregrosa/jaiskills. It costs 11 tokens per session (262 once invoked), scanned A, original, MIT.

A command that runs a constatar plan file from start to finish and checks the recorded results. Constatar is a tool for running planned work and verifying each unit with evidence.

In plain words
What is it for?
Use it to execute plan.toml files, monitor progress, inspect verification evidence and cost, and identify failed units for later resumption.
Why use it?
It gives you a recorded, repeatable result instead of relying on an agent's own claim that the work succeeded. It also stops when the repository is uncommitted or required adapters are missing.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the jaiskills plugin — 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to execute plan.toml files, monitor progress, inspect verification evidence and cost, and identify failed units for later resumption.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jairotorregrosa/jaiskills/constatar-run
Install

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.

Clone the repo
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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 constatar-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/constatar-run/github.svg)](https://agentmods.dev/commands/jairotorregrosa/jaiskills/constatar-run)
Your own site
<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/constatar-run"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/constatar-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 constatar-run

Your own site · 80×15
<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/constatar-run"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/constatar-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 262 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 $0.00011 $0.00262
Opus 5 $0.00005 $0.00131
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 9d ago against content hash 2fd1cff404c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

constatar-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 9d 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.

commands/constatar-run.md · 15 lines

What it actually says

Execute a constatar plan end to end.

  1. Load the constatar-verify and constatar-plan skills' rules (verification ladder, invariants).
  2. constatar preflight — abort with the error if adapters are missing.
  3. Parse arguments: $ARGUMENTS = plan file, optional run dir (default runs/<plan-name>-<date>).
  4. If the plan's repo has uncommitted changes, stop and tell the user (the engine will refuse with DirtyRepo; do not stash or commit for them without asking).
  5. constatar run <plan> --run-dir <run-dir> — stream progress to the user.
  6. On success: constatar inspect --conformance --run-dir <run-dir> --plan <plan> --assert-all-pass, then summarize per unit: verification rungs passed, evidence highlights, cost (inspect --cost).
  7. On failure: report the failing unit, rung, and error verbatim; list surviving constatar/<unit> branches; suggest constatar resume after the cause is fixed. Never re-run units by hand.
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. 9d ago First seen · 15 lines · 11 tokens per session scan A 2fd1cff404c2

Subscribe to this mod's changes

constatar-run is a command published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 9d ago), licensed MIT. It adds 11 tokens to every session and 262 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.