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 alexei-led/architect --skill architecture-plangit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/architecture-plan)<a href="https://agentmods.dev/skills/alexei-led/architect/architecture-plan"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/architecture-plan.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.02078 |
| Opus 5 | $0.00049 | $0.01039 |
| Sonnet 5 | $0.00020 | $0.00416 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade B, and why
architecture-plan scanned grade B with 1 finding 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 7d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Keep task names outcome-based. Do not expose prompt or tool internals in task How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture plan
Derive an actionable, incremental implementation/refactoring plan from an approved design, with review findings as supporting context when present. The artifact is executable by an engineer, mutator agent, or task runner; the architect writes the plan and stops.
When to use
Use after an architecture design, when the user wants approved target
architecture implemented. For existing-code remediation, the default chain is
architecture-review → architecture-design → architecture-plan. Plan one
hotspot, boundary, module, or flow per plan unless a roadmap is explicitly
requested.
If there is no approved design artifact, recommend architecture-design first.
If there is no review report for existing-code remediation, recommend
architecture-review before design unless the user explicitly wants greenfield
target-state design.
Skill navigation
- Missing findings for an existing system: recommend
architecture-reviewfirst unless the user already supplied enough current evidence. - Missing approved target architecture: recommend
architecture-designbefore planning. - Current skill: use
architecture-planto sequence small, verifiable changes from an approved design, citing review findings as supporting rationale when present. - Next skill after implementation: run
architecture-reviewto verify the code now matches intended architecture and the plan's acceptance criteria.
Task list discipline
Maintain a visible task list for the planning flow. Track at least:
- Approved design artifact confirmed; supporting review report confirmed when present.
- Scope and first execution horizon selected.
- Safety net ordered before behavior-bearing changes.
- Executable task sections drafted.
- Verification and acceptance criteria attached.
- Handoff and re-review step recorded.
Keep task names outcome-based. Do not expose prompt or tool internals in task names.
Destination
When the user explicitly asks for a plan file and gives no destination, ask to
confirm the default path under docs/plans/ using a kebab-case slug from the
target, for example docs/plans/extract-auth-boundary.md. Create docs/plans/
only after the destination is confirmed. If the user only asks to generate or
create a plan, return it in the conversation unless they confirm a file path.
Use a user-specified path only when provided. If the user-specified path is
outside docs/plans/, state that the executor must be invoked with that exact
path or the plan must be copied/symlinked into the configured plans directory.
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.
- 7d ago First seen · 190 lines · 98 tokens per session scan B d007499cb54c
architecture-plan is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 2,078 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…