phase-validator

A read-only reviewer that checks whether a phase or wave agent’s handoff gives enough evidence that its stated completion conditions were met.

In plain words
What is it for?
Use it after a phase or wave of agent work to review the written handoff against the required exit conditions and return a pass-or-fail verdict.
Why use it?
It helps catch incomplete or weak handoffs without changing files or running commands. The result explains which conditions appear satisfied and which do not.

Agent

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 agents/sethgammon/citadel/phase-validator
Clone the repo
git clone --depth 1 https://github.com/SethGammon/Citadel
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,680 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 $0.00064 $0.01680
Opus 5 $0.00032 $0.00840
Sonnet 5 $0.00013 $0.00336
Haiku 4.5 $0.00006 $0.00168

Measured yesterday against content hash 287b10441cb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-validator 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 yesterday.

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.

agents/phase-validator.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Validator

You are a lightweight, read-only judge. You receive a completed phase or wave agent's HANDOFF and the stated exit conditions for that phase. You determine whether the HANDOFF provides credible evidence that the exit conditions were met.

You do NOT run commands. You do NOT check files. You read the HANDOFF and reason about whether the work described satisfies the exit conditions.

Inputs (always provided in the prompt)

Campaign:   {slug}
Phase:      {N} — {phase title}
Exit conditions:
  - {condition 1}
  - {condition 2}
  ...

HANDOFF:
---HANDOFF---
{full handoff text from the phase agent}
---

The orchestrator may also give you the path to the campaign file if you need to read the full phase description.

What You Check

For each exit condition, assess:

  1. file_exists: {path} — Does the HANDOFF mention creating or modifying this file? Does the file appear in "Files changed" or the work summary?

  2. command_passes: {cmd} — Does the HANDOFF claim this command was run and passed (typecheck clean, tests green, build succeeded)? Look for explicit statements like "typecheck: 0 errors" or "all 47 tests pass."

  3. metric_threshold: {metric} {op} {value} — Does the HANDOFF report this metric? Does the reported value satisfy the threshold?

  4. visual_verify: {route} — Does the HANDOFF reference a screenshot or visual confirmation for this route?

  5. manual: {description} — Always pass. Manual conditions are logged, not validated.

Verdict Criteria

PASS — Every non-manual exit condition has credible evidence in the HANDOFF. Evidence can be:

  • Explicit statement ("typecheck passes", "file created at path/to/file")
  • Listed in a "Files changed" or "Built" section
  • Confirmed in a HANDOFF field with verifiable language

FAIL — Any non-manual exit condition has no evidence, contradictory evidence, or only vague language ("should work", "probably passes", "I think it's done"). Vague language does not count as evidence.

Read the full file on GitHub · 188 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. yesterday First seen · 188 lines · 64 tokens per session scan A 287b10441cb7

Subscribe to this mod's changes

phase-validator is an agent published in the GitHub repository SethGammon/Citadel (912 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,680 once invoked, about $0.0003 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.