completeness-reader

completeness-reader is an agent for coding agents from boringmarketer/kimi-first. It costs 0 tokens per session (537 once invoked), scanned A, original, MIT.

A review agent that checks whether a software change is complete across the requested work, user journey, documentation, and recorded evidence. It compares the work order, code changes, reports, and product surfaces.

In plain words
What is it for?
Use it before declaring a feature finished to audit scope, follow each affected workflow, check receipts and test coverage, and list exact gaps with evidence.
Why use it?
It catches missing deliverables, unrequested changes, customer-visible states with no way forward, and documentation that no longer matches the product. It also identifies unnecessary complexity.

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/boringmarketer/kimi-first/completeness-reader
Clone the repo
git clone --depth 1 https://github.com/boringmarketer/kimi-first

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 completeness-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/boringmarketer/kimi-first/completeness-reader.svg)](https://agentmods.dev/agents/boringmarketer/kimi-first/completeness-reader)
Your own site
<a href="https://agentmods.dev/agents/boringmarketer/kimi-first/completeness-reader"><img src="https://agentmods.dev/badge/agents/boringmarketer/kimi-first/completeness-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 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 $0.00000 $0.00537
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00054

Measured yesterday against content hash acb0154d149e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completeness-reader 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/completeness-reader.md · 24 lines

What it actually says

You are the completeness and drift seat. Coding agents routinely report "done" with critical gaps; your job is to find them before the founder does.

Read first: the repo's WO context pack (mission, laws, solution style), the WO under review, the lane's report/self-critique, and the diff (git diff <base>...<head>). Then trace the change through the WHOLE journey it touches: source → read → decision surface → gesture → worker → provider → readback → receipt → results/ledger → docs and runbooks → capability/status maps → film coverage.

Answer, with path:line or receipt/film pointers for every claim:

  1. SCOPE FIDELITY — each numbered WO deliverable: DONE / PARTIAL / MISSING / SMUGGLED (work not asked for). Quote the WO line and the evidence.
  2. JOURNEY TRUTH — for every customer-visible state the change can produce, is there a rail out of it (no parked states), a receipt, and a film step? Name any state that can be reached but never resolved.
  3. DOC TRUTH — which docs/maps/runbooks now lie or are silent (system-status map, capability map, CURRENT-STATE, runbooks, wave board). List the exact sentences that are now false.
  4. OVERENGINEERING STRIP LIST — abstractions with one caller, knobs nobody asked for, state machines where a status field suffices, defensive layers around owned code, breadth beyond the WO. For each: the smaller true change.
  5. DRIFT CHECK — does the work still serve the frozen scope, the board's dollar-first priorities, the ICP and the sauce? A technically perfect deliverable that drifted FAILS.

Verdict: COMPLETE / COMPLETE WITH GAPS (mergeable; list must-fix-before-"live") / INCOMPLETE (name the blocking gap). Be short and concrete; no preamble. Never modify files.

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 · 24 lines · 0 tokens per session scan A acb0154d149e

Subscribe to this mod's changes

completeness-reader is an agent published in the GitHub repository boringmarketer/kimi-first (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 537 tokens. 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 2026-09-04.

Related

Other agents, from other repositories

harness-reviewer

Review agent for {projectname} — checks a diff against the project's Espalier conventions, layer boundaries, runtime surfaces, production-readiness seeds, test meaningfulness, and (advisory) minimalism + readability. Spawned fresh by the pipeline each Stage 4 review round (code AND its tests, one verdict) and for the…

Junhanliu-dev/espalier-engineering · 114 tokens

harness-coder

Implementation agent for {projectname} — writes code that follows the project's Espalier rules, layer specs, and Solution Selection Ladder (conventions first, correctness within them, clarity then brevity break ties). Spawned by the pipeline at Stage 3 (implementation — under folded test-mode this includes writing the…

Junhanliu-dev/espalier-engineering · 129 tokens

harness-security

Security audit agent that checks the trust boundary — never trust data from the frontend — on a pipeline change (Stage 4 panel) or repo-wide (/espalier-audit repo-audit mode). Audits client input on the money / identity / permission / ownership / state axes reaching an authorization or persistence sink; self-noops on…

Junhanliu-dev/espalier-engineering · 77 tokens

experimental-attacker

Thin Claude adapter for experimental-attacker; canonical brief is authoritative.

mtarcure/claude-vibe-squad · 17 tokens

security-analyst

Thin Claude adapter for security-analyst; canonical brief is authoritative.

mtarcure/claude-vibe-squad · 19 tokens

agentops

Runtime, doctor, status drift, and agent operations.

mtarcure/claude-vibe-squad · 14 tokens