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 pjt222/agent-almanac --skill adapt-architecturegit 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/skills/pjt222/agent-almanac/adapt-architecture)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/adapt-architecture"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/adapt-architecture/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/pjt222/agent-almanac/adapt-architecture"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/adapt-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.02986 |
| Opus 5 | $0.00048 | $0.01493 |
| Sonnet 5 | $0.00019 | $0.00597 |
| Haiku 4.5 | $0.00010 | $0.00299 |
Grade A, and why
adapt-architecture 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 6d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapt Architecture
Execute structural metamorphosis — transforming a system's architecture from its current form to a target form while maintaining operational continuity. Uses strangler fig migration, chrysalis phases, and interface preservation to ensure the system never stops functioning during transformation.
When to Use
- Form assessment (see
assess-form) classified the system as READY - A system must evolve its architecture to meet new requirements without downtime
- Migrating from monolith to microservices (or the reverse)
- Replacing a core subsystem while dependent systems continue operating
- Evolving a data model while maintaining backward compatibility
- Any architectural change that must be gradual rather than big-bang
Inputs
- Required: Current form assessment (from
assess-formor equivalent analysis) - Required: Target architecture (what the system should become)
- Required: Operational continuity requirements (what must not break during transformation)
- Optional: Available transformation budget (time, people, compute)
- Optional: Rollback requirements (how far back must we be able to retreat?)
- Optional: Parallel running duration (how long to run old and new simultaneously)
Procedure
Step 1: Design the Transformation Blueprint
Plan the metamorphosis path from current form to target form.
- Map the transformation as a sequence of intermediate forms:
- Current form → Intermediate form 1 → ... → Target form
- Each intermediate form must be operationally viable (can serve traffic, pass tests)
- No intermediate form should be harder to maintain than the current form
- Identify the transformation seams:
- Where can the current form be "cut" to insert the new architecture?
- Natural seams: existing interfaces, module boundaries, data partitions
- Artificial seams: interfaces created specifically to enable the cut (anti-corruption layers)
- Choose the metamorphosis pattern:
- Strangler fig: new system grows around the old, gradually replacing it
- Chrysalis: old system is wrapped in a new shell; internals replaced while shell preserves external interface
- Budding: new system grows alongside the old; traffic gradually shifts (see
scale-colonyfor colony budding) - Metamorphic migration: phased replacement of components in dependency order (leaves first, roots last)
- Design the interface preservation layer:
- External consumers must not experience disruption
- API versioning, backward-compatible contracts, adapter patterns
- The preservation layer is temporary scaffolding — plan its removal
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.
- 6d ago First seen · 234 lines · 96 tokens per session scan A 4f38a5b6cf0e
adapt-architecture is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,986 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
analytics
Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs…
design-feature
Turn a raw idea or existing feature into a designed product SPEC by completing entity, integration, role, and expectation closure. Upserts never destroy recorded decisions. Triggers: "design-feature", "design this feature", "define product scope".
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
plan-feature
Route designed features or issues into engineering planning and roadmap registration; undesigned work stops at design-feature. Supports --next, --from-issue, and --scaffold. Triggers: "plan-feature", "plan a feature", "plan the next roadmap feature", "create SPEC and TASKS".
product-audit
Audit the whole product across code, quality, process, docs, roadmap, and tooling. Persist one severity-ranked, F-numbered report with proposals; never fix or file work. Triggers: "product-audit", "audit the product", "full health check", "are we product-ready", "CTO review".
audit-docs
Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them…