spec-manager

spec-manager is a skill for Claude Code, Codex from loki-ai-ch/spec-manager. It costs 33 tokens per session (962 once invoked), scanned A, original, MIT.

A spec-driven project workflow that moves software work from a product requirements document to a design, implementation specification, and coding task, with human approval between stages.

In plain words
What is it for?
Use it to start or run feature tasks, create requirements and designs, plan iterations, prepare tests and releases, write operating guides, document incidents and architecture decisions, and describe incremental changes.
Why use it?
It records the decisions needed for non-trivial work and requires an approved implementation specification before code is changed.

Skill for Claude CodeCodex

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 skills/loki-ai-ch/spec-manager/codebuddy-skill
Any agent
npx skills add loki-ai-ch/spec-manager --skill codebuddy-skill
Clone the repo
git clone --depth 1 https://github.com/loki-ai-ch/spec-manager

Made for: Claude Code, Codex.

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 spec-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/loki-ai-ch/spec-manager/codebuddy-skill.svg)](https://agentmods.dev/skills/loki-ai-ch/spec-manager/codebuddy-skill)
Your own site
<a href="https://agentmods.dev/skills/loki-ai-ch/spec-manager/codebuddy-skill"><img src="https://agentmods.dev/badge/skills/loki-ai-ch/spec-manager/codebuddy-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 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 $0.00033 $0.00962
Opus 5 $0.00016 $0.00481
Sonnet 5 $0.00007 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 3d ago against content hash 79e84a305b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-manager 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 3d 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.

.claude/skills/spec-manager/templates/agents/codebuddy-skill/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

spec-manager

Use this skill when the user invokes /spec-manager, asks for a new feature, PRD, technical design, implementation spec, agent task, iteration plan, test plan, release notes, runbook, postmortem, ADR, or delta change.

Entry Points

  • /spec-manager <request> — start from the user's requirement and route to the right subskill.
  • /spec-manager run <taskId> — execute an existing Agent Task.

Unified Rules

  • 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.

Read the full file on GitHub · 60 lines

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. 3d ago First seen · 60 lines · 0 tokens per session scan A 79e84a305b19

Subscribe to this mod's changes

spec-manager is a skill published in the GitHub repository loki-ai-ch/spec-manager (5 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 962 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.

Related

Other skills, from other repositories

diagnose

Turn a bug symptom into a fix with a regression test that locks it down. If the user opens vague ("there's a bug", "/diagnose"), interview them one question at a time until you have enough to attempt a reproduction; if you still cannot reproduce, say so explicitly. Then drive the work through five phases — build a…

eduwxyz/my-awesome-skills · 0 tokens

tdd

Drives feature work and bug fixes through a tight failing-test-first loop. Trigger when implementing, fixing, or refactoring behavior in a codebase that already has tests. Skip for spikes, visual-only edits, throwaway scripts, and generated files.

eduwxyz/my-awesome-skills · 53 tokens

verify

Verify that a spec.md's Acceptance criteria are observably covered by green tests before opening a PR. Reads the spec, finds the tests that cover each AC, runs the suite to confirm everything green, and reports gaps (uncovered AC, skipped tests, missing edge-case coverage). When gaps exist, automatically iterates with…

eduwxyz/my-awesome-skills · 149 tokens

spec-approach

Add a refined ## Approach section to an existing feature spec.md before TDD executes it. Reads the spec, explores the codebase to ground the approach in real modules and patterns, proposes 2–3 alternatives when they exist, validates with the user, then appends ## Approach to the same spec file. Trigger after…

eduwxyz/my-awesome-skills · 125 tokens

feature

Kick off the full feature workflow — interview-to-spec, optional spec-approach, tdd, verify, then review — when starting a new feature from scratch. Thin orchestrator: confirms intent in one sentence, then hands off to the first stage and lets each downstream skill activate on its own. Trigger when the user says "new…

eduwxyz/my-awesome-skills · 0 tokens

interview-to-spec

Conduct a focused interview to draft a spec.md for an upcoming task (the input step of SDD — spec-driven development). Walks through goal, behaviors, acceptance criteria, edge cases, and out-of-scope one branch at a time, then writes the spec to disk. If during the interview the scope turns out to be multiple…

eduwxyz/my-awesome-skills · 136 tokens