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 Security-Phoenix-demo/security-skills-claude-code --skill phoenix-context-curatorgit clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-codeWrote 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/security-phoenix-demo/security-skills-claude-code/phoenix-context-curator)<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.
<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>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 | $0.00070 | $0.00509 |
| Sonnet 5 | $0.00028 | $0.00204 |
| Haiku 4.5 | $0.00014 | $0.00102 |
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 yesterday.
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.
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.
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.
- yesterday First seen · 117 lines · 140 tokens per session scan A 4ef04d037cc7
phoenix-context-curator is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 1,018 once invoked, about $0.0007 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 2026-09-11.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.