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 agentmods add skills/evolplus/talos/evo-devkit-contractnpx skills add evolplus/talos --skill evo-devkit-contractgit clone --depth 1 https://github.com/evolplus/talosWhat 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 | $0.00046 | $0.03738 |
| Opus 5 | $0.00023 | $0.01869 |
| Sonnet 5 | $0.00009 | $0.00748 |
| Haiku 4.5 | $0.00005 | $0.00374 |
Grade A, and why
evo-devkit-contract 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — End-to-End Development Workflow
This file is the operating contract for Claude Code on this repository. The main Claude instance acts as the Project Orchestrator (PM). It does not implement work directly; it delegates to specialized sub-agents and owns the integrity of the project state.
This file holds the four always-on sections every agent must follow: §1 Source of Truth, §2 SRS Sign-off Protocol,
§6 Open Issues, §10 Hard Rules. Operational mechanics live in .claude/rules/ and are indexed below. Section numbers
are preserved across files so cross-references in agent templates (e.g., §3.1, §4) resolve via this index.
Rule Index
| Section | Topic | Location |
|---|---|---|
| §1 | Source of Truth (3-row authoritative table; full artifact-ownership detail) | this file + .claude/rules/artifact-ownership.md |
| §2 | SRS Sign-off Protocol (status enum + invariant; full procedural detail) | this file + .claude/rules/srs-signoff-protocol.md |
| §3 | Roles (Sub-Agents) | .claude/rules/sub-agent-registry.md |
| §3a | Sub-Agent Registry | .claude/rules/sub-agent-registry.md |
| §4 | Parallel Execution + Design Lifecycle | .claude/rules/parallel-execution.md |
| §5 | Worktree Isolation | .claude/rules/worktree-isolation.md |
| §6 | Open Issues — Mandatory Triage Gate | this file |
| §7 | Change Synchronization | .claude/rules/change-synchronization.md |
| §8 | Master Plan Discipline | .claude/rules/master-plan-discipline.md |
| §9 | Orchestrator Operating Rules | .claude/rules/orchestrator-operating-rules.md |
| §10 | Hard Rules (universal Hard Rules; role-specific + hook-enforced detail) | this file + .claude/rules/hard-rules.md |
| §11 | Task Type Routing | .claude/rules/task-type-routing.md |
| §12 | Brownfield Onboarding (incl. documentation-only sub-case) | .claude/rules/brownfield-onboarding.md |
| §13 | Workload Tier — throughput / parallelism dial | .claude/rules/workload-tier.md |
| §14 | Crash Recovery & Dispatch Reconciliation | .claude/rules/crash-recovery.md |
| §15 | Autonomous Execution Loop (/sdlc-loop run-to-gate driver) |
.claude/rules/autonomous-loop.md |
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.
- 2d ago First seen · 146 lines · 46 tokens per session scan A 3387ff60b3b1
evo-devkit-contract is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 28d ago), licensed Apache-2.0. It adds 46 tokens to every session and 3,738 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…