framing-coverage-honored

framing-coverage-honored is an agent for coding agents from infraspecdev/tesseract. It costs 82 tokens per session (612 once invoked), scanned A, original, MIT.

A research-quality checker that verifies whether a findings document includes the required voices and source types from its framing brief. A framing brief is the plan that defines whose views and what kinds of sources the research must cover.

In plain words
What is it for?
Use it during research review to check that every required voice has a direct quote and every required source category is represented in the findings body.
Why use it?
It reveals when a research summary appears complete but has omitted required perspectives or evidence from the main text.

Agent

Part of the shield plugin — 17 agents shipped together

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/framing-coverage-honored
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract

Or install shield, the plugin that ships this one along with the rest of its 17 agents.

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 framing-coverage-honored

README.md
[![agentmods](https://agentmods.dev/badge/agents/infraspecdev/tesseract/framing-coverage-honored.svg)](https://agentmods.dev/agents/infraspecdev/tesseract/framing-coverage-honored)
Your own site
<a href="https://agentmods.dev/agents/infraspecdev/tesseract/framing-coverage-honored"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/framing-coverage-honored.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 612 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 $0.00082 $0.00612
Opus 5 $0.00041 $0.00306
Sonnet 5 $0.00016 $0.00122
Haiku 4.5 $0.00008 $0.00061

Measured 3d ago against content hash 9853f9e96e8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

framing-coverage-honored 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 3d 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/framing-coverage-honored.md · 56 lines

What it actually says

Framing Coverage Honored (PM11)

Description

Grade ONE PM dimension — Research-Review ONLY: does the synthesized findings document honor the framing brief that originally shaped the research? Each PF7 must-cite voice MUST appear with a direct quote in the body (not just in References). Each PF8 required source type MUST have at least one direct quote in the body. Missing items become the most actionable feedback this reviewer can give. Return a single-check JSON block — no prose.

Inputs

  • findings_path — absolute path to the synthesized research findings document
  • framing_brief_path — absolute path to the PF1-PF8 framing brief produced by shield:research-framer

If framing_brief_path is missing, return grade N/A with reasoning — this check cannot run without the brief.

Check

ID Eval point Severity Pass criterion
PM11 Framing coverage honored Important Every PF7 voice listed in the framing brief appears with a direct quote in the BODY of the findings (not just References). Every PF8 source type marked "Required? yes" has at least one direct quote in the body. Missing items grade C-F depending on count; complete coverage grades A.

Grade A (fully met) / B (1 minor miss) / C (2-3 misses) / D (>3 misses) / F (>half missing).

Output shape (JSON only)

{
  "id": "PM11",
  "name": "Framing coverage honored",
  "persona": "product-manager",
  "grade": "A|B|C|D|F|N/A",
  "severity": "Important",
  "na_reasoning": "<required if grade N/A; otherwise omit or null>",
  "missing_pf7_voices": ["<name>"],
  "missing_pf8_source_types": ["<type>"],
  "evidence_quote": "<verbatim line from the findings, or empty string>",
  "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 findings 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. 3d ago First seen · 56 lines · 82 tokens per session scan A 9853f9e96e8a

Subscribe to this mod's changes

framing-coverage-honored is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 612 once invoked, about $0.0004 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.