injection-fidelity

injection-fidelity is a skill for Claude Code, Codex from yogsoth-ai/de-anthropocentric-research-engine. It costs 58 tokens per session (1,074 once invoked), scanned A, original, Apache-2.0.

A judging procedure for checking whether a simulated user followed a predefined pressure plan during a conversation. It measures behaviors such as asking for evidence, requesting operational details, defending incorrect assumptions, and introducing new ideas.

In plain words
What is it for?
It is for evaluating dialogue samples axis by axis against a policy card, using only the specified conversation turns and behavior signals.
Why use it?
It separates whether the simulation followed its assigned behavior from whether the underlying research or answer was good.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It is for evaluating dialogue samples axis by axis against a policy card, using only the specified conversation turns and behavior signals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity
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 yogsoth-ai/de-anthropocentric-research-engine --skill injection-fidelity
Clone the repo
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine

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 injection-fidelity

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity/github.svg)](https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity)
Your own site
<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for injection-fidelity

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/de-anthropocentric-research-engine/injection-fidelity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,074 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 pass 7 Sept 2026
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 $0.00058 $0.01074
Opus 5 $0.00029 $0.00537
Sonnet 5 $0.00012 $0.00215
Haiku 4.5 $0.00006 $0.00107

Measured 11d ago against content hash c39becb0ccda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

injection-fidelity 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 11d 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.

ladder-foundry/skills/injection-fidelity/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

injection-fidelity (loss-1)

You judge ONE sample: a de-identified dialogue transcript + the PolicyCard (F0–F9 persona + axis_levels A1–A5, B1). Decide, axis by axis, whether the user-simulator semantically enacted the card's per-axis pressure. You judge "was the card enacted", never "is the research good". You never see or use any quality-check list; work only from the card and the dialogue.

Pressure window

Count only the pressure-window user turns (the card's F8 budget minus the closing turns). Normalize every rate by that count (pressure_turns).

The 6 signals → axes

Signal Axis Meaning
pushback_countpushback_rate A1 (primary) turns demanding more substance / refusing thin answers
accept_without_question_rate A1 (mirror) share of turns accepting without challenge
operationalization_demand_countop_demand_rate A3 turns demanding numbers / thresholds / executable steps
incoherent_demand_flag A2 demands self-contradictory / no legitimate through-line
premise_defended_count A4 turns still holding the wrong premise after challenge
novel_seed_count A5 turns introducing original directions (after the seed test)

Event bits: premise_dropped / premise_revised (A4 trajectory).

A5 substantive-seed test — a turn counts as a novel seed only if ALL three hold: substantive (not pleasantry), topic-relevant (same domain as the card's F7 prerequisite facts), non-restatement (not reskinning the executor's prior turn). Each counted seed carries a quote + the 3 judgments in per_axis_evidence.A5.

Expected bands (continuous axes A1, A3)

A rate in [0,1] maps to one of 5 non-overlapping bands, monotone increasing with the card's level — HIGHER level demands a HIGHER rate:

  • L0 = [0, .10], L1 = (.10, .30], L2 = (.30, .55], L3 = (.55, .80], L4 = (.80, 1]

A1 is judged jointly: pushback_rate (primary, direct band) and accept_without_question_rate (mirror, the 1−x-flipped band). The two directions must agree; if they contradict, A1 fails.

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 82 lines · 58 tokens per session scan A c39becb0ccda

Subscribe to this mod's changes

injection-fidelity is a skill published in the GitHub repository yogsoth-ai/de-anthropocentric-research-engine (456 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,074 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.

Related

Other skills, from other repositories

Deep Research

Produce a deep, structured research report on a topic: decompose into key dimensions, analyze each with evidence and reasoning, synthesize cross-cutting insights, and surface open questions. Use for deep research, analysis, and literature/landscape reviews.

AgentEra/Agently · 53 tokens

literature-review-tools

Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use to ..." for…

brycewang-stanford/lit-review-agent-tools · 288 tokens

papers-reading-skill

Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text, Markdown, or a text-based PDF; separate source-grounded claims from researcher analysis; bind findings to…

AOROM/paperreading · 115 tokens

paper-fulltext-harvest

Batch download academic paper full-text (PDF/XML) from a list of DOIs. Handles 25 DOI prefixes across 19 publisher families via three layered routes: (1) publisher TDM APIs requiring institutional subscription (Elsevier ScienceDirect, Wiley Online, Springer Nature), (2) Open Access sources (Crossref, Unpaywall…

jxtse/scientific-research-skills · 276 tokens

academic-figure-generation

Generates publication-quality academic figures (framework diagrams, pipeline illustrations, system architectures, method overviews) from a paper's method text and a target caption, using a local PaperBanana multi-agent pipeline (Retriever → Planner → Stylist → Visualizer → Critic).

jxtse/scientific-research-skills · 59 tokens

paper-reading

Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden…

jxtse/scientific-research-skills · 154 tokens