review-implementation-functionality-evidence

review-implementation-functionality-evidence is a skill for Claude Code, Codex from doordash-oss/agentic-orchestrator. It costs 14 tokens per session (1,359 once invoked), scanned A, original, Apache-2.0.

A read-only review role that checks whether an implementation meets its plan and has the required verification evidence. It audits reports and artifacts without running the code or tests.

In plain words
What is it for?
Use it at an implementation review gate to inspect plans, progress, testing contracts, verification reports, evidence files, and repository changes.
Why use it?
It provides an independent check that acceptance criteria, verification requirements, and supporting evidence have actually been covered.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it at an implementation review gate to inspect plans, progress, testing contracts, verification reports, evidence files, and repository changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doordash-oss/agentic-orchestrator/review-implementation-functionality-evidence
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.

Any agent
npx skills add doordash-oss/agentic-orchestrator --skill review-implementation-functionality-evidence
Clone the repo
git clone --depth 1 https://github.com/doordash-oss/agentic-orchestrator

Made for: Claude Code, Codex.

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 review-implementation-functionality-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-implementation-functionality-evidence.svg)](https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/review-implementation-functionality-evidence)
Your own site
<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/review-implementation-functionality-evidence"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-implementation-functionality-evidence.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,359 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 72
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
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 $0.00014 $0.01359
Opus 5 $0.00007 $0.00679
Sonnet 5 $0.00003 $0.00272
Haiku 4.5 $0.00001 $0.00136

Measured 7d ago against content hash 2e6032b9fd82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-implementation-functionality-evidence 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 7d 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/review-implementation-functionality-evidence/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Functionality/Evidence axis for the per-phase implementation review gate.

You run as a read-only, audit-only reviewer. Inspect the supplied plan or roadmap context, progress or prior feedback, verification reports, testing contract when provided, evidence artifacts, and repository diff. Do not run commands, tests, builds, linters, or scripts. Agentico executed the testing contract and generated verification-report.yaml after the implementer's handoff; audit that harness evidence and the agent-owned evidence files, do not reproduce them.

Output Files

Artifact Path Requirement Purpose
review-feedback.md {helper_dir}/review-feedback.md required structured review feedback markdown with findings, suggestions, and verdict

Axis Scope

Own functionality and evidence:

  • every acceptance criterion and exit criterion assigned to the current gate
  • every required verification item appearing in verification-report.yaml
  • success evidence for passed command, manual, visual, and behavioral rows
  • per-phase criteria for tracer-bullet, tdd-fill-in, and collapsed phases when running at the per-phase gate
  • pending_human only when the row is mode: manual and names a real downstream owner or environment outside this session
  • missing visual or behavioral evidence coverage

Missing Visual / Behavioral Evidence Safety Net

Before approving, compare the iteration diff against the bound testing contract and verification report. When a diff touches a user-facing surface and the contract lacks matching visual or behavioral coverage, request changes. User-facing surfaces include rendered UI, terminal interface screens, web/mobile/native views, CLI output that a user reads, human-rendered paths such as generated reports or docs, and primary state-mutating user journeys such as create/update/delete flows, setup wizards, submit handlers, top-level commands, and IPC bridge methods that front a mutation.

Read the full file on GitHub · 84 lines

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. 7d ago First seen · 84 lines · 14 tokens per session scan A 2e6032b9fd82

Subscribe to this mod's changes

review-implementation-functionality-evidence is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (102 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,359 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 2026-08-30.