narrative-sensemaking

narrative-sensemaking is a skill for Claude Code from cdeust/zetetic-team-subagents. It costs 79 tokens per session (704 once invoked), scanned A, original, MIT.

A method for reconstructing what happened and what it meant from accounts such as incident reports, postmortems, user journeys, and roadmaps. It examines roles, order, missing steps, and whether a claimed sequence is structurally possible.

In plain words
What is it for?
Use it to analyze failure narratives, user journeys, sequential workflows, incident responses, and authoritative-sounding claims.
Why use it?
It helps when the main problem is understanding a story or workflow rather than measuring a technical mechanism. It can expose gaps, out-of-order steps, and claims that do not fit the described process.

Skill for Claude Code

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

Part of the zetetic-team-subagents plugin — 16 skills, 2 commands, 23 agents, 7 hooks, 1 MCP server shipped together

Good fit Use it to analyze failure narratives, user journeys, sequential workflows, incident responses, and authoritative-sounding claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cdeust/zetetic-team-subagents/narrative-sensemaking
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 cdeust/zetetic-team-subagents --skill narrative-sensemaking
Clone the repo
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagents

Made for: Claude Code.

Or install zetetic-team-subagents, the plugin that ships this one along with the rest of its 16 skills, 2 commands, 23 agents, 7 hooks, 1 MCP server.

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 narrative-sensemaking

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdeust/zetetic-team-subagents/narrative-sensemaking/github.svg)](https://agentmods.dev/skills/cdeust/zetetic-team-subagents/narrative-sensemaking)
Your own site
<a href="https://agentmods.dev/skills/cdeust/zetetic-team-subagents/narrative-sensemaking"><img src="https://agentmods.dev/badge/skills/cdeust/zetetic-team-subagents/narrative-sensemaking/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 narrative-sensemaking

Your own site · 80×15
<a href="https://agentmods.dev/skills/cdeust/zetetic-team-subagents/narrative-sensemaking"><img src="https://agentmods.dev/badge/skills/cdeust/zetetic-team-subagents/narrative-sensemaking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 704 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.
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 $0.00079 $0.00704
Opus 5 $0.00039 $0.00352
Sonnet 5 $0.00016 $0.00141
Haiku 4.5 $0.00008 $0.00070

Measured 11d ago against content hash 8a9b760fb276, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

narrative-sensemaking 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.

skills/narrative-sensemaking/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narrative Sensemaking

Problem shape: the material is an account — an incident write-up, a user journey, a roadmap story, a vendor claim, a postmortem — and the work is to recover its structure: which functions occur in which order, which roles are filled, where the sequence breaks its own grammar, and whether the account is even structurally possible. Paradigmatic/causal analysis is the wrong mode here and produces confident nonsense when forced.

Relevant geniuses

Agent Use when
bruner the question is "what happened and what did it mean?" — decide narrative vs paradigmatic mode explicitly, then analyze the breach of the canonical script that made the event tellable
propp a sequential process (workflow, pipeline, user journey, incident response) needs its invariant functions extracted, its roles abstracted from their current occupants, and its gaps found by grammar rather than by inspection
ibnkhaldun a claim sounds authoritative but may be structurally impossible — filter on structural plausibility before evaluating the source; check whether the reported thing could occur at that scale at all

Invocation

  1. Pick the best-fit agent above. If two or more fit, run tools/genius-invoker.sh route "<problem>" and take the top ranked match.
  2. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read agents/genius/<agent>.md in full.
  3. Apply the agent's <workflow> step by step and answer in its <output-format>. State which mode the account is being read in — narrative or paradigmatic — before drawing any conclusion from it.
  4. Typical chain: ibnkhaldun filters out the structurally impossible → propp extracts the function sequence from what survives → bruner reads what the breach meant to the people in it. Run via tools/genius-invoker.sh compose ibnkhaldun propp bruner -- "<problem>".
  5. If no shape above matches, do not force a genius — use a standard team agent (INDEX.md routing rule).

Read the full file on GitHub · 53 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. 11d ago First seen · 53 lines · 79 tokens per session scan A 8a9b760fb276

Subscribe to this mod's changes

narrative-sensemaking is a skill published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 704 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.

Related

Other skills, from other repositories