rollback-check

rollback-check is a command for coding agents from iampawan/Manifest. It costs 40 tokens per session (438 once invoked), scanned A, original, MIT.

A read-only rollout health check that compares live error, crash, adoption, and performance signals with the limits defined for a feature. A rollout gradually releases a change to users, often as a canary—a small initial group.

In plain words
What is it for?
Use it during a rollout to check whether the feature is within its agreed limits and decide what a human should do next.
Why use it?
It turns production data into a clear recommendation to continue, pause, or consider reverting, without making that production change automatically.

Command

Part of the manifest plugin — 28 skills, 15 commands shipped together

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.

agentmods
npx agentmods add commands/iampawan/manifest/rollback-check
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

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 rollback-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/iampawan/manifest/rollback-check.svg)](https://agentmods.dev/commands/iampawan/manifest/rollback-check)
Your own site
<a href="https://agentmods.dev/commands/iampawan/manifest/rollback-check"><img src="https://agentmods.dev/badge/commands/iampawan/manifest/rollback-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.00438
Opus 5 $0.00020 $0.00219
Sonnet 5 $0.00008 $0.00088
Haiku 4.5 $0.00004 $0.00044

Measured 4d ago against content hash 04dc5288590c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rollback-check 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 4d 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/rollback-check.md · 49 lines

What it actually says

/rollback-check

Runs the rollback-guard skill for a contract that is currently rolling out. Samples Sentry errors, crash-free rate, release adoption, and perf against the contract's budgets, and returns a recommendation.

Usage

/rollback-check SC-005

What it does

  1. Reads the contract's budgets (perfBudget, crash-free / error budgets, optional rollbackTriggers).
  2. Samples live signals via Sentry / Crashlytics / APM for the rollout window.
  3. Emits a schema-checked verdict (scripts/validate.mjs --check-guard):
    • proceed — healthy, keep ramping.
    • hold — a warning or low confidence; pause the ramp, investigate.
    • recommend-rollback — a clear breach; recommends reverting and posts a top-level Slack alert to the owner.
  4. Writes a guard report and stamps guardVerdict on the contract.

Important

This command recommends; it never acts. Pausing a canary, flipping a flag, or rolling back is a production change a human approves and performs. The guard gives you the defensible call and the exact action to take — you pull the trigger.

When to use

  • Manually, any time during a rollout you want a health read.
  • Automatically on a tight cadence via rollback-guard.yml while a canary is live (canaryStartedAt set, prodRollout100At not yet).

See also

  • /verify-deploy — pre-rollout readiness verdict
  • /launch — the slower day 1/7/14/28 "did it land" reports
  • reference/CONTRACT-FORMAT.mdrollbackTriggers + guard fields
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. 4d ago First seen · 49 lines · 40 tokens per session scan A 04dc5288590c

Subscribe to this mod's changes

rollback-check is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 438 once invoked, about $0.0002 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.