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.
npx skills add JinPLu/clear-eyed-reading-skills --skill clear-eyed-readinggit clone --depth 1 https://github.com/JinPLu/clear-eyed-reading-skillsWrote 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.
[](https://agentmods.dev/skills/jinplu/clear-eyed-reading-skills/clear-eyed-reading)<a href="https://agentmods.dev/skills/jinplu/clear-eyed-reading-skills/clear-eyed-reading"><img src="https://agentmods.dev/badge/skills/jinplu/clear-eyed-reading-skills/clear-eyed-reading/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.
<a href="https://agentmods.dev/skills/jinplu/clear-eyed-reading-skills/clear-eyed-reading"><img src="https://agentmods.dev/badge/skills/jinplu/clear-eyed-reading-skills/clear-eyed-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.03492 |
| Opus 5 | $0.00057 | $0.01746 |
| Sonnet 5 | $0.00023 | $0.00698 |
| Haiku 4.5 | $0.00012 | $0.00349 |
Grade A, and why
clear-eyed-reading 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 12d 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.
This is a copy
86% identical to clear-eyed-deep-reading — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared Clear-Eyed Reading Core
Help a reader with no prior exposure understand the work and take back interpretive and evaluative control from the authors' terminology, branding, and narrative. Demystify by completing four judgments: reconstruct the ordinary mechanism; trace where capabilities or knowledge come from; identify the genuine increment over the closest prior work; and explain how the reported result came about, whether the conclusion is warranted, or what lets a system do what it shows. Let this independent reconstruction raise or lower the evaluation. Critique claims and evidence, never the authors.
Four judgments
Keep these four judgments, and do not substitute a summary, a limitation list, or a popularity report for any of them:
- Ordinary mechanism — after names and branding are removed, what enters, what happens, and what leaves.
- Capability sources — which data, prior models, assumptions, rules, labels, human choices, instruments, implementation, post-processing, scale, or evaluation choices supply the observed ability.
- Genuine increment — for every important candidate contribution, what is inherited, what technically changed relative to the closest primary precedent, and what the field would lose without that change.
- Result attribution — what actually carries the result or conclusion, and which rival explanations remain consequential.
Scale verification to risk and depth
Identify the work and the version the conclusion will rest on. Never fill gaps from an abstract, caption, search snippet, or guess; say what cannot be checked.
Scale how far to read and search by two factors: conclusion risk (how much the four judgments would change if this were wrong) and the active depth profile. High-risk conclusions—technical novelty, field significance, that the new method caused the result, reuse readiness, claim stability, or that a weakness is absent—need correspondingly stronger primary evidence. The depth profile sets the search budget; it does not change what the four judgments mean.
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.
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.
- 12d ago First seen · 127 lines · 115 tokens per session scan A bd99f99549f3
clear-eyed-reading is a skill published in the GitHub repository JinPLu/clear-eyed-reading-skills (4 stars, last pushed 26d ago), licensed MIT. It adds 115 tokens to every session and 3,492 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to clear-eyed-deep-reading, differing in 24 lines, and is treated as a copy.
Other skills, from other repositories
report-slides
Use when creating presentations and research reports, especially diagram-heavy decks with architecture, flowcharts, timelines, charts, conceptual illustrations, or editable PPTX output.
academic-paper
12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE…
academic-pipeline
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification…
academic-paper-reviewer
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on…
deep-research
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring…
research-log
Record, manage, and query research experiment logs. Use when the user wants to log an experiment result, amend an existing entry, view recent logs, rebuild the index, or plan, execute, repeat, or diagnose research in a project containing docs/researchlog/. Triggers on phrases like "log this experiment", "record…