performing-close-reading

performing-close-reading is a skill for Claude Code from icerain-cmd/humanities-superpowers. It costs 40 tokens per session (2,288 once invoked), scanned A, original, MIT.

A method for interpreting a specific passage, image, interface, performance, or other source by separating what can be directly observed from the conclusions drawn from it. It requires the source, enough context, and a clear question.

In plain words
What is it for?
Producing observation notes, evidence-based interpretations, rival readings, context checks, and a report showing whether the source supports the requested analysis.
Why use it?
It prevents broad or unsupported interpretations by linking each claim to visible or otherwise verifiable details and by considering an alternative reading.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the humanities-superpowers plugin — 14 skills shipped together

Good fit Producing observation notes, evidence-based interpretations, rival readings, context checks, and a report showing whether the source supports the requested analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/icerain-cmd/humanities-superpowers/performing-close-reading
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 icerain-cmd/humanities-superpowers --skill performing-close-reading
Clone the repo
git clone --depth 1 https://github.com/icerain-cmd/humanities-superpowers

Made for: Claude Code.

Or install humanities-superpowers, the plugin that ships this one along with the rest of its 14 skills.

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 performing-close-reading

README.md
[![agentmods](https://agentmods.dev/badge/skills/icerain-cmd/humanities-superpowers/performing-close-reading.svg)](https://agentmods.dev/skills/icerain-cmd/humanities-superpowers/performing-close-reading)
Your own site
<a href="https://agentmods.dev/skills/icerain-cmd/humanities-superpowers/performing-close-reading"><img src="https://agentmods.dev/badge/skills/icerain-cmd/humanities-superpowers/performing-close-reading.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,288 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Data Exfiltration · line 66
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 $0.00040 $0.02288
Opus 5 $0.00020 $0.01144
Sonnet 5 $0.00008 $0.00458
Haiku 4.5 $0.00004 $0.00229

Measured 8d ago against content hash cc8cf069c13c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

performing-close-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 8d 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.

skills/performing-close-reading/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performing Close Reading

Purpose

Produce accountable interpretations by separating what is observable in an object from the interpretive moves made about it. The skill keeps quotation, description, inference, contextual claim, and theoretical implication distinct while allowing them to interact.

Contract

Accepts

  • A supplied passage, image, scene, interface, recording, performance description, archival item, or material artifact.
  • Provenance and context available to the researcher.
  • A research question or claim to test.

Requires

  • Direct access to the object or a reliable reproduction.
  • Enough context to avoid obvious misidentification or truncation.
  • A stated analytical purpose.

Produces

  • Observation records.
  • Interpretive inferences linked to observed features.
  • At least one rival reading.
  • Contextual claims requiring verification.
  • A close-reading gate report.

May produce

  • A revised local claim.
  • A list of additional contextual sources needed.
  • FAIL when the object is unavailable, corrupted, mistranscribed, or insufficient for the requested conclusion.

Fails when

  • The requested analysis depends on an object not supplied or reliably accessible.
  • Quoted language cannot be distinguished from paraphrase.
  • The interpretation requires invented context, authorial intention, or source history.
  • The requested conclusion exceeds what the object can establish.

Guarantees

  • Observations and interpretations are separately labeled.
  • Every interpretive claim points to at least one specific feature.
  • Rival readings and evidentiary limits remain visible.

Does not guarantee

  • A uniquely correct interpretation.
  • Historical representativeness, authorial intention, or broader causal explanation.
  • That local evidence alone can support the manuscript’s largest claim.

When to use

Use with literary, philosophical, visual, cinematic, digital, performative, architectural, archival, and interface objects. Use when a draft moves from quotation directly to theme, when theory substitutes for attention, or when a single local feature is made to represent an entire period or culture.

Read the full file on GitHub · 287 lines

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. 8d ago First seen · 287 lines · 40 tokens per session scan A cc8cf069c13c

Subscribe to this mod's changes

performing-close-reading is a skill published in the GitHub repository icerain-cmd/humanities-superpowers (16 stars, last pushed 17d ago), licensed MIT. It adds 40 tokens to every session and 2,288 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 2026-08-30.