prioritization-rationale

A review agent for checking whether a product plan explains its order of work and the reasons for that order. It examines dependencies and the balance between effort and expected impact.

In plain words
What is it for?
Use it to review product plans, research documents, proposals, and other documents that need justified phases and priorities.
Why use it?
It exposes plans that are only unsequenced task lists or that give no reason for doing one phase before another. This makes dependencies and delivery priorities easier to assess.

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/infraspecdev/tesseract/prioritization-rationale
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 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 $0.00038 $0.00404
Opus 5 $0.00019 $0.00202
Sonnet 5 $0.00008 $0.00081
Haiku 4.5 $0.00004 $0.00040

Measured 2d ago against content hash 9f6e838d7def, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prioritization-rationale 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 2d 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.

shield/agents/prioritization-rationale.md · 45 lines

What it actually says

Prioritization Rationale (PM4)

Description

Grade ONE PM dimension: does the document explain the SEQUENCE the work happens in, with effort-vs-impact reasoning and dependencies surfaced? Return a single-check JSON block — no prose.

Inputs

  • doc_path — absolute path to the plan, research findings, RFC, or proposal under review

Check

ID Eval point Severity Pass criterion
PM4 Prioritization rationale Important The plan sequences work with a stated rationale: effort or impact estimates per phase, named dependencies between phases, justification for why phase N comes before phase N+1. A flat to-do list without sequencing fails. Sequenced phases without rationale grade C-D.

Grade A (fully met) / B (minor gap) / C (partial) / D (barely) / F (absent).

Output shape (JSON only)

{
  "id": "PM4",
  "name": "Prioritization rationale",
  "persona": "product-manager",
  "grade": "A|B|C|D|F",
  "severity": "Important",
  "evidence_quote": "<verbatim line from the doc, or empty string if absent>",
  "gap": "<one sentence, or null if grade A>",
  "suggestion": "<one sentence, or null if grade A>"
}

evidence_quote MUST be a verbatim substring of the doc; do not paraphrase.

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. 2d ago First seen · 45 lines · 38 tokens per session scan A 9f6e838d7def

Subscribe to this mod's changes

prioritization-rationale is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 404 once invoked, about $0.0002 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 2026-08-31.