What is phoenix-context-curator?

A context-cleaning step that organises raw notes, tickets, chat discussions, and customer-call transcripts into facts, decisions, and unanswered questions.

Use it to prepare Phoenix project context, identify relevant customers and integrations, and provide structured input to the scope-definition step.

It separates confirmed information from assumptions and unknowns before the team makes scope or design decisions.

phoenix-context-curator — Skill by Security-Phoenix-demo

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 Security-Phoenix-demo/security-skills-claude-code --skill phoenix-context-curator

Clone the repo

git clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-code

Made for: Claude Code.

Or install phoenix-prd-pipeline, the plugin that ships this one along with the rest of its 13 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator/github.svg)](https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator)

Your own site

<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,018 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.

Model	Per session	Once invoked
Fable 5.1	$0.00140	$0.01018
Opus 5.5	$0.00056	$0.00407
Sonnet 5.5	$0.00028	$0.00204
Haiku 4.5	$0.00014	$0.00102

Measured 1mo ago against content hash 4ef04d037cc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phoenix-context-curator 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 1mo 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/phoenix-prd-pipeline/skills/phoenix-context-curator/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phoenix Security — Context Curator (Role 01)

Token Budget: ≤900 tokens Feeds Into: Role 02 — Scope Cutter Output: 01-clean-context.md

Phoenix Domain Vocabulary (use consistently)

Term	Meaning
ASPM	Application Security Posture Management — Phoenix's core product
CTEM	Continuous Threat Exposure Management
Container Lineage	Image → deployment → exploit chain tracing
Reachability	Code-path-aware vuln prioritisation (not CVSS-only)
SCA	Software Composition Analysis
SBOM	Software Bill of Materials
DevSecOps	Security gates in CI/CD (Jenkins, GitHub Actions)
CNAPP	Cloud-Native Application Protection Platform
KEV	CISA Known Exploited Vulnerabilities
Maturity Model	Phoenix risk scoring model (Johnson Matthey use case)
Board-Level Risk	10-category risk reporting (Anaplan use case)

Phoenix Integration Surface

Cloud: AWS (onboarding + core), GCP (Phoenix CTI + AI models)
Security Tools: GitHub AS, Snyk, Qualys, Prisma (being displaced), Wiz, Azure SC
Dev Tools: Jenkins, GitHub Actions, Backstage
Stack: Python/Flask, PowerShell, N8N, Gemini (custom LLM), Claude API

Task

Given raw context, classify every item into exactly ONE bucket:

FACT — observed / confirmed / measurable
DECISION — chosen tradeoff / policy / constraint
OPEN_QUESTION — unknown, disputed, or customer-dependent

Then identify contradictions and competitor mentions.

Core Rules

Do not invent facts, APIs, constraints, policies, or architecture. Ask if missing (max 7 questions).
Open questions are unknown — never spec based on them.
Every MUST must be verifiable or it's not a MUST.
Tag customer-specific context: (account: Mimecast|JohnsonMatthey|Anaplan)
Flag competitor mentions: Prisma, Wiz, ArmorCode, Snyk → add COMPETITOR_FLAG
If contradictions exist, call them out — do not paper over them.
Output must be internally consistent.

Read the full file on GitHub · 117 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.

1mo ago First seen · 117 lines · 140 tokens per session scan A 4ef04d037cc7

Subscribe to this mod's changes

phoenix-context-curator is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (81 stars, last pushed 5d ago), licensed MIT. It adds 140 tokens to every session and 1,018 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-11.

Project management Writing and docs

phoenix-context-curator next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
phoenix-context-curatorSecurity-Phoenix-demo/security-skills-claude-code	Skill	81	5d ago	MIT	A	140	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code