Skip to content
Back to skills

Evidence Gate

ASecurity

Assess whether verification evidence and scope integrity support merge review. Produces a confidence report and Builder merge-readiness evidence.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 16, 2026
ai-agentsrustbash

Works with

  • cli

Security analysis

A100/100

Scanned October 16, 2026

npx -y skills add kontourai/flow-agents --skill evidence-gate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Evidence Gate?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Evidence Gate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kontourai-evidence-gate/badge)](https://www.skillsdirectory.com/skills/kontourai-evidence-gate)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "evidence-gate"
description: "Assess whether verification evidence and scope integrity support merge review. Produces a confidence report and Builder merge-readiness evidence."
---

# Evidence Gate

## Role

This is a Builder step skill.

Evidence Gate assesses whether the completed work has trustworthy, scoped
evidence for merge review. It does not fix code, publish a change, approve a
release, or deploy.

## Binding

| Context | Binding | Flow expectation |
| --- | --- | --- |
| Active Builder run | `builder.build` at `merge-ready` | `merge-readiness` |
| Standalone invocation | No Flow binding | No workflow mutation. |

For an active run, confirm the binding before evaluation:

The steering hook injects the run state at session start and re-injects it whenever it changes; if a steering state block appears anywhere in your context and you have not recorded evidence or a critique since it appeared, it is current. Run `flow-agents workflow status --session-dir <session-dir> --json` only after such a write or when no steering state block appears in your context at all; the write itself refuses an unbound, stale, or wrong-step binding either way.

Only a matching run may publish `merge-readiness`. A standalone confidence
report is local and must not call `workflow evidence`.

## Inputs

- The relevant verification and critique slices in `trust.bundle`.
- Changed-file scope from `RepositoryAdapter` or the execution record.
- Change and check records from `ChangeProvider` and `CheckProvider` when available.
- Known risks, accepted gaps, and repository policy evidence.

## Evaluation

Aggregate the existing canonical implementation scope, accepted criteria,
critique, observed commands, and available provider records. Reuse their exact
references and revision bindings. This step adds a confidence decision; it does
not require a second criterion ledger or another run of current checks.

1. Operate report-only. Do not patch source, alter checks, publish a change, or
   rerun with weaker options to manufacture a passing decision.
2. Confirm acceptance evidence maps to the intended changed scope. Compare the
   planned scope, actual diff, generated files, and provider-reported change.
   Unexplained drift, weakened checks, or unrelated edits reduce confidence and
   must be named.
3. Classify evidence by strength: direct runtime or test observation; provider
   check/review record; reproducible command result; source inspection; or
   unsupported assertion. Preserve command, revision, timestamp, scope, and
   artifact provenance where available. Prose-only completion claims are not
   acceptance proof.
4. Re-run only to resolve an actual stale result, changed scope, contradiction,
   or missing required observation, and only when the command is safe and
   reproducible. A stale,
   unavailable, changed, or non-reproducible check is degraded to
   `NOT_VERIFIED`; a previous pass must not remain current by assertion.
5. Produce `PASS`, `FAIL`, or `NOT_VERIFIED` for the confidence decision.
   `NOT_VERIFIED` is the result for missing required proof, unavailable provider
   information, or unresolved integrity questions.
6. On a matching active run, publish the decision through the public CLI:

```bash
flow-agents workflow evidence --session-dir <session-dir> \
  --expectation merge-readiness \
  --status <pass|fail|not_verified> \
  --summary "Evidence confidence, scope integrity, and remaining risks are recorded." \
  --evidence-ref-json '{"kind":"artifact","file":"<session-dir>/<slug>--evidence-gate.md","summary":"Evidence confidence, criterion coverage, and scope-integrity decision."}'
```

## Output

Record the confidence report as the `merge-readiness` slice in `trust.bundle`.
It contains the scope assessed, acceptance evidence, integrity findings,
evidence provenance, residual risks, `PASS`/`FAIL`/`NOT_VERIFIED` decision, and
recommended route.

Reuse the existing readable `Acceptance Evidence` table or canonical criterion
references when behavior is claimed. Add a table only when it resolves a scope
or evidence gap; do not copy the ledger merely to satisfy this step:

| AC id | Status | Command/Test Evidence | Source Evidence | Gaps |
| --- | --- | --- | --- | --- |

For a matching active run, publish that report as `merge-readiness`. This is a
merge-review confidence decision, not release or deployment authorization.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.