agentmods.dev

CLAUDE

CLAUDE is an agent for Claude Code from loki-ai-ch/spec-manager. It costs 0 tokens per session (480 once invoked), scanned A, original, MIT.

A project instruction for Claude that routes feature work through spec-manager, a tool for writing and approving detailed plans before coding.

In plain words
What is it for?
It helps Claude create, approve, freeze, and verify feature specifications, then start coding tasks from those specifications.
Why use it?
It prevents code from being written before the intended behavior is agreed and recorded. It also keeps implementation tasks linked to their approved requirements.

Agent for Claude Code

not rated 5 1mo ago A scan 0 tokens original MIT
View the source file loki-ai-ch/spec-manager
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.

agentmods
npx agentmods add agents/loki-ai-ch/spec-manager/claude
Clone the repo
git clone --depth 1 https://github.com/loki-ai-ch/spec-manager

Made for: Claude Code.

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.

agentmods badge for CLAUDE

README.md
[![agentmods](https://agentmods.dev/badge/agents/loki-ai-ch/spec-manager/claude.svg)](https://agentmods.dev/agents/loki-ai-ch/spec-manager/claude)
Your own site
<a href="https://agentmods.dev/agents/loki-ai-ch/spec-manager/claude"><img src="https://agentmods.dev/badge/agents/loki-ai-ch/spec-manager/claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00480
Opus 5 $0.00000 $0.00240
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 4d ago against content hash 2d9b90571f8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CLAUDE 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • CODEBUDDY — 88% identical, 16 lines differ
.claude/skills/spec-manager/templates/agents/CLAUDE.md · 18 lines

What it actually says

Spec-Driven Development

This project uses spec-manager via the /spec-manager skill.

  • Feature work MUST go through spec-manager.
  • New or non-trivial work follows L1 -> L2 -> L3 -> Agent Task.
  • Never write implementation code without a frozen L3 spec.
  • L1/L2 approval advances draft -> confirmed; one explicit L3 approval (an explicit user approval) advances draft -> frozen.
  • Before code edits, read the frozen L3 spec and create/start an Agent Task.
  • planJson coveredSpecs MUST include the current L3 specCode.
  • If adaptive workflow is enabled, Task creation records a standard or governed Profile snapshot; governed requires the frozen L3 to declare ## 关键验收标准 with valid AC IDs, and task complete requires successful verification evidence covering every critical AC. standard reports missing coverage as warnings. Use spec-manager project profile recommend --request "<work>" for a deterministic, explainable recommendation; it does not auto-enable adaptive workflow and is not a hidden gate. Use spec-manager project profile metrics [--topic <topic>] [--json] for a read-only governance report over Profile adoption, governed coverage gaps, standard warnings, and explicit overrides; metrics does not modify config or historical Tasks. Use spec-manager project readiness critical [--topic <topic>] [--json] for a read-only critical AC readiness report and repair suggestions; it must not auto-generate or insert critical AC. Before enabling adaptive workflow, use spec-manager project workflow preview [--json] for a read-only adoption preview; preview does not write config, migrate historical Tasks, or act as an enable gate.
  • quick remains a restricted lightweight exception and does not create the full L1/L2/L3/Task chain.
  • Validate L3 markdown plans with spec-manager spec validate-plan --from-spec <L3-code>.
  • Record execution with spec-manager task step; finish with spec-manager task complete.
  • For research, prefer spec-manager spec show metadata first, then --include-content when full context is required.

Use the installed .claude/skills/spec-manager/ skill when the user invokes /spec-manager or approves the next spec-manager step.

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.

  1. 4d ago First seen · 18 lines · 0 tokens per session scan A 2d9b90571f8e

Subscribe to this mod's changes

CLAUDE is an agent published in the GitHub repository loki-ai-ch/spec-manager (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 480 tokens. 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.

ai-agentsai-codingcli-toolharnesssddspec-driven-development
Related

Other agents, from other repositories

architect

Drafts an Architecture document for a SpecManager feature, grounded in the approved PRD AND the existing codebase. Reads repo source/conventions before writing.

joanseg/specmanager · 33 tokens

walkthrough-writer

Writes a per-phase Walkthrough document for a SpecManager feature, or — in phase: "final" mode — a feature-level roll-up that links each phase walkthrough.

joanseg/specmanager · 40 tokens

reviewer

Read-only spec-compliance reviewer. Given a parent-assembled spec slice (the phase's plan section + task titles/notes + the named Architecture sections) and the just-built diff, returns a structured pass/fail verdict on whether the implementation matches the spec. Never writes. Invoked by /specmanager-build after the…

joanseg/specmanager · 79 tokens

doc-onboard

Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.

christopherlouet/claude-base · 34 tokens

ops-infra-code

Infrastructure as Code (Terraform, OpenTofu). Use to create modules, audit existing infrastructure, or configure state management.

christopherlouet/claude-base · 29 tokens

legal-privacy-policy

GDPR privacy policy generation. Use to create or update the privacy policy.

christopherlouet/claude-base · 20 tokens