triage-pregraph-data

triage-pregraph-data is a skill for Claude Code from narrative-io/narrative-skills-marketplace. It costs 196 tokens per session (7,195 once invoked), scanned A, original, MIT.

A skill for checking data or access rules before they are added to an identity graph, a system that links identifiers belonging to the same entity. It looks for suspicious identifiers, unusually connected records, and other patterns that could merge unrelated entities.

In plain words
What is it for?
Use it to audit pre-graph data, test data-quality hypotheses, measure effects on rows, links, and entities, and recommend cautious filters before building the combined identity graph.
Why use it?
Bad links can spread through a graph and combine many distinct people or accounts into one group. The skill measures the likely damage and bases filtering suggestions on evidence from the dataset.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the narrative-identity plugin — 3 skills shipped together

Good fit Use it to audit pre-graph data, test data-quality hypotheses, measure effects on rows, links, and entities, and recommend cautious filters before building the combined identity graph.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data
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 narrative-io/narrative-skills-marketplace --skill triage-pregraph-data
Clone the repo
git clone --depth 1 https://github.com/narrative-io/narrative-skills-marketplace

Made for: Claude Code.

Or install narrative-identity, the plugin that ships this one along with the rest of its 3 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 triage-pregraph-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data/github.svg)](https://agentmods.dev/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data)
Your own site
<a href="https://agentmods.dev/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data"><img src="https://agentmods.dev/badge/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data/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 triage-pregraph-data

Your own site · 80×15
<a href="https://agentmods.dev/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data"><img src="https://agentmods.dev/badge/skills/narrative-io/narrative-skills-marketplace/triage-pregraph-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,195 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: 3 findings, 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 System Prompt Leakage · line 136
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • medium Excessive Agency · line 597
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 602
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00196 $0.07195
Opus 5 $0.00098 $0.03598
Sonnet 5 $0.00039 $0.01439
Haiku 4.5 $0.00020 $0.00720

Measured 12d ago against content hash 82f1a43e45c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

triage-pregraph-data 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.

plugins/narrative-identity/skills/triage-pregraph-data/SKILL.md · 623 lines

How it starts

The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Pre-Graph Data

Persona

You are a graph-quality engineer auditing a dataset before it joins an identity-graph build. You optimize for:

  1. Defensible thresholds — every filter you propose is tied to quantified evidence from this dataset, never to a rule from a prior build and never to intuition.
  2. Conservative removal under transitivity — connected-components is transitive, so one bad edge can collapse thousands of distinct entities into a single giant component. You bias toward removing identifiers when the evidence supports it, and you quantify the damage radius before recommending action.
  3. Combined-graph realism — most sources are UNIONed with others in the downstream build, not used standalone. Filter decisions account for that: behaviorally implausible per-entity activity (e.g., a single person carrying 400+ identifiers) is itself defensible evidence for filtering, even when the standalone bridge potential within this one source is bounded — because UNIONing with other sources will propagate the bad attachment into other components. Phase 2 explicitly pins standalone vs. combined; when in doubt, assume combined.
  4. Minimal cuts — you remove bad edges while preserving as much legitimate signal as possible. Maximal filters are easy and wrong.

You never apply a threshold from a prior dataset without re-justifying it here. You never recommend a filter without quantified before/after impact. You never treat "bad" as universal — what counts as a problem depends on the identifier type, the source system, what realistic behavior looks like for the entity being identified, and whether this source will be combined with others downstream.

Output rules

Don't surface _nio_* field names to the user. Columns and fields whose names start with _nio_ (e.g., _nio_last_modified_at, _nio_sample_128) are platform-managed internals. Handle them silently as this skill instructs — filtering, skipping, or accepting auto-generated mappings — but do not name them in user-facing output: lists, tables, summaries, warnings, status messages, or final responses. Refer to them generically ("platform-managed columns", "reserved internal fields") if you need to acknowledge them at all.

Read the full file on GitHub · 623 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. 12d ago First seen · 623 lines · 196 tokens per session scan A 82f1a43e45c4

Subscribe to this mod's changes

triage-pregraph-data is a skill published in the GitHub repository narrative-io/narrative-skills-marketplace (8 stars, last pushed today), licensed MIT. It adds 196 tokens to every session and 7,195 once invoked, about $0.0010 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

ops-demo

CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.

Snowflake-Labs/cocoplus · 46 tokens

managing-astro-local-env

Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.

astronomer/agents · 63 tokens

checking-freshness

Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.

astronomer/agents · 44 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

agent-team-orchestration

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…

LeoYeAI/openclaw-master-skills · 102 tokens

diary

Show CocoDiary operator-facing work journal status.

Snowflake-Labs/cocoplus · 12 tokens