
On this page
Before you start Start with checks the project already owns Declare what particular changes require Inspect freshness after editing Read the result where you workA useful coding result includes more than "done." You need to know what changed, which checks ran, and whether those results still apply to the files you are reviewing. CLIO Coder v0.8.0 can use your repository's declared checks and a project quality policy to make those questions explicit.
Before you start
- A Git repository with a test or build check it already declares, such as a package script or a CI step.
- CLIO Coder with a model that supports tool calling.
- Time to read the resolved command each check runs.
Start with checks the project already owns
The verifier derives checks from supported build systems, project scripts, and CI definitions. When it cannot resolve a requested check, it should not substitute an arbitrary command and call it a pass.
Run this project's test check through verify. Report its exit status, failures, and anything you could not check.

Read the resolved command and working directory in the tool activity. A recognized test runner runs without a card, and other commands may ask first. verify is subject to command admission: naming a check does not grant permission to run it, and a denied command is not a validation result.
When a command does ask, the terminal approval card names the tool and the exact command. Its effect row says in plain words what a recognized command changes, and warns when CLIO Coder cannot classify the command at all.

The tools guide covers discovery and execution. The temperature-calibration example follows a small numerical correction with recorded test results.
Declare what particular changes require
A quality policy selects required checks by changed path. At the Git workspace root:
.clio-coder/quality.yaml
version: 1
rules:
- id: source
paths: ["src/**", "tests/**"]
inputs: ["src/**", "tests/**", "package.json", "package-lock.json"]
checks: [test]
allowLimitations: falseName the changes a rule covers
pathsselects the rule: here, any change undersrc/ortests/.List every input the result depends on
inputsfeeds freshness. Include fixtures, configuration, helper files, and lockfiles; this example assumes the root package declares atestscript and keeps npm's lockfile. A pnpm or Yarn project listspnpm-lock.yamloryarn.lockinstead.verifyruns a package script asnpm run <id>either way.Name existing checks, not commands
checksrefers to declared checks. A policy cannot insert an arbitrary shell command or bypass approvals.Decide whether limitations are acceptable
allowLimitations: falsemeans a reported limitation does not satisfy the rule.
CLIO Coder does not write this policy for you. Review it as a repository contract: a command that passes a narrow subset of tests should not satisfy a policy that requires the full declared test check.
Inspect freshness after editing
When a passing check still counts
Your project
Declared check
A package script, build target, or CI definition the project already owns.
verify runs it
Results
Recorded pass
Stored with source, check-declaration, and policy fingerprints.
an input changes
Assessment
Stale
The earlier pass no longer describes the files.
verify runs again
Assessment
Current
A result for the work that exists now.
CLIO Coder compares source, check-declaration, and policy fingerprints. A passing check becomes stale after relevant inputs change, and a later failure supersedes an earlier pass of the same check.
This matters during an iterative fix. The agent might run a test, make another edit, and then summarize the earlier success. The current assessment should describe the work that exists now, not the best result observed along the way.
Required checks run through verify without argument or working-directory overrides. Declare subproject checks with the correct working directory in the supported catalog or a root script. The quality-policy guide explains check identity and freshness.
Read the result where you work
On the desktop alpha, the Session column's Artifacts card lists outputs and session records, Changes lists the files a turn changed, and Evidence appears once a run has a record. In the terminal, /view opens artifacts and run records.

What to look for
The actual check, its result, and any missing evidence. A sealed run record is an inspectable account of the run, and clio-coder telemetry verify checks its journals. It is not a certificate that every scientific or operational requirement was met.
Boundaries
- Snapshots need Git and a workspace at the repository root. They cover tracked and nonignored untracked source within the documented bounds.
- They do not establish the state of external datasets, installed dependencies, running services, or other hidden inputs.
- A valid policy selects high rigor by default and asks to continue for outstanding checks when recovery is possible; normal rigor makes the assessment advisory. Neither grants extra execution authority.
- Numerical comparisons, integration tests, and human review may still be necessary.