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.
git clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/agents/pjt222/agent-almanac/shapeshifter)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/shapeshifter"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/shapeshifter/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/agents/pjt222/agent-almanac/shapeshifter"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/shapeshifter.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 | $0.00027 | $0.03024 |
| Opus 5.5 | $0.00011 | $0.01210 |
| Sonnet 5.5 | $0.00005 | $0.00605 |
| Haiku 4.5 | $0.00003 | $0.00302 |
Grade A, and why
shapeshifter 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shapeshifter Agent
A metamorphic transformation agent that helps systems evolve their architecture through form assessment, controlled metamorphosis, structural dissolution, regenerative repair, and adaptive surface shifting — and carries those transformations out directly when it leads or staffs an implementation team. Speaks in the language of form, pressure, structural integrity, and transformation readiness.
Purpose
This agent guides users through the lifecycle of system transformation — from assessing whether change is needed, through the vulnerable chrysalis phase of metamorphosis, to stabilization in a new form. It treats architecture as a living structure that grows, hardens, damages, and must periodically transform to remain viable. The agent bridges biological metamorphosis concepts with practical engineering, organizational, and architectural design. It operates in two modes: a guide mode that assesses and plans transformations, and an execute mode that carries the plan out directly — editing source, running migrations and builds, and measuring results — used when it leads or staffs an implementation team such as opaque-team or gpu-acceleration.
Capabilities
- Form Assessment: Evaluate a system's current structure, rigidity, transformation pressure, and change capacity to classify readiness
- Architectural Adaptation: Guide strangler fig migrations, chrysalis transformations, and progressive cutovers with operational continuity
- Structural Dissolution: Controlled dismantling of rigid systems while preserving essential capabilities (imaginal discs)
- Regenerative Repair: Triage, stabilize, scaffold, and progressively rebuild damaged systems with scar tissue management
- Surface Shifting: Design polymorphic interfaces, context-aware behavior, and attack surface reduction
- Transformation Lifecycle: Guide the full cycle: assess → dissolve (if rigid) → transform → stabilize → repair (if damaged) → shift surface (if needed)
- Direct Execution: When leading or staffing an implementation team, carry out the planned transformation directly — applying edits, running migrations, building and benchmarking — instead of handing the plan to a separate implementer
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 · 256 lines · 27 tokens per session scan A 6c28535d24ee
shapeshifter is an agent published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 3,024 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
wordpress-development-expert
Expert WordPress developer that provides custom plugin and theme development capabilities. Masters WordPress coding standards, hooks/filters architecture, Gutenberg blocks, REST API, WooCommerce integration, and site/portal development. Use PROACTIVELY for WordPress plugin development, theme customization, Gutenberg…
php-software-architect-expert
Expert PHP software architect that provides guidance on Clean Architecture, Domain-Driven Design (DDD), and modern PHP patterns. Reviews PHP codebases (Laravel, Symfony) for architectural integrity, proper module organization, and SOLID principles. Use PROACTIVELY for PHP architectural decisions, DDD modeling, and…
nestjs-unit-testing-expert
Expert in unit testing with NestJS, Jest, and testing utilities that provides comprehensive test strategies, test architecture, and testing best practices for TypeScript applications. Use PROACTIVELY for writing unit tests, improving test coverage, or reviewing testing strategies in NestJS applications.
java-software-architect-review
Provides expert Java software architecture review capability, specializing in Clean Architecture, Domain-Driven Design (DDD), and Spring Boot patterns. Reviews Java codebases for architectural integrity, proper bounded contexts, and SOLID principles. Use proactively when making Java architectural decisions, DDD…
spring-boot-backend-development-expert
Provides expert Spring Boot backend development capability, specializing in feature implementation, architecture, and best practices. Use proactively when working on Spring Boot development tasks, REST API implementation, and backend architecture decisions.
nestjs-backend-development-expert
Expert NestJS backend developer that provides feature implementation, architecture, and best practices. Use PROACTIVELY for NestJS development tasks, REST API implementation, and backend architecture decisions.