What is phoenix-constraint-distiller?

A constraint-setting step that turns a feature scope into a short list of testable rules for later requirements and designs.

Use it to record the Phoenix constraints that apply to a feature, such as AWS and GCP responsibilities, supported security tools, reachability-based prioritisation, and limits on autonomous AI actions.

It keeps downstream work aligned with fixed architecture, team capacity, tenant isolation, authentication, integrations, and AI safety expectations.

phoenix-constraint-distiller — 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-constraint-distiller

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-constraint-distiller/github.svg)](https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-constraint-distiller)

Your own site

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

Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 881 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	$0.00164	$0.00881
Opus 5.5	$0.00066	$0.00352
Sonnet 5.5	$0.00033	$0.00176
Haiku 4.5	$0.00016	$0.00088

Measured 1mo ago against content hash 250d5941c7cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phoenix-constraint-distiller 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-constraint-distiller/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phoenix Security — Constraint Distiller (Role 03)

Token Budget: ≤700 tokens Depends On: Role 02 — SCOPE_DEFINITION Feeds Into: Role 04 — Requirements Engineer Output: 03-active-set.md

Phoenix Standing Constraints (PSC)

Evaluate all for inclusion. Include only those relevant to the current feature.

ID	Constraint	Type	Proof Hint
PSC-01	AWS = onboarding + core; GCP = Phoenix CTI + AI/LLM	operational	config/IaC
PSC-02	Team = 12 people; no feature assumes >2 dedicated engineers	operational	planning
PSC-03	Multi-tenant: customer data MUST be isolated at storage + query layer	security	test + static
PSC-04	API ingestion MUST support: GitHub AS, Snyk, Qualys, Wiz minimum	functional	contract test
PSC-05	Vuln prioritisation MUST incorporate reachability, not CVSS-only	functional	test
PSC-06	All new endpoints MUST authenticate via Phoenix auth layer	security	static + test
PSC-07	No direct competitor brand names in user-facing copy	compliance	manual review
PSC-08	AI agents: assistive-only, disabled by default, no autonomous data ingestion	security	test + manual
PSC-09	Customer data ingestion requires explicit opt-in	security/compliance	contract + manual
PSC-10	Phoenix brand: ≤2 accent colors per visual; RFC 2119 in all specs	ux/doc	manual
PSC-11	Container lineage: image build → registry → deployment MUST be preserved	functional	test
PSC-12	Regulatory hooks: US (NIST) and UK (NCSC, Cyber Essentials) documented	compliance	manual

Core Rules

Constraints must be actionable and testable.
No duplicates — merge overlapping constraints.
No "nice-to-have" fluff.
Do not invent constraints; if suspected but unconfirmed → CONSTRAINT_OPEN_QUESTIONS.
Always include ≥1 security constraint (PSC-03 or PSC-06 or equivalent).
Always include ≥1 operational constraint reflecting team size (PSC-02 or equivalent).
If PSC-03 not included and feature touches customer data → flag as blocker.

Read the full file on GitHub · 86 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 · 86 lines · 164 tokens per session scan A 250d5941c7cb

Subscribe to this mod's changes

phoenix-constraint-distiller 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 164 tokens to every session and 881 once invoked, about $0.0007 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.

Planning Security

phoenix-constraint-distiller next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
phoenix-constraint-distillerSecurity-Phoenix-demo/security-skills-claude-code	Skill	81	5d ago	MIT	A	164	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