task-spec-freezer

task-spec-freezer is an agent for Claude Code from mussolene/1c_hbk_bsl. It costs 22 tokens per session (214 once invoked), scanned A, original, MIT.

A planning agent that turns a repository task into fixed scope, acceptance criteria, assumptions, exclusions, and a verification plan. Acceptance criteria are the specific conditions that must be met for the task to count as complete.

In plain words
What is it for?
Use it to review relevant project memory, preserve the original request, define AC1-style criteria, and prepare verification without changing production code.
Why use it?
It prevents the implementation from drifting and makes the expected result testable before code changes begin.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Good fit Use it to review relevant project memory, preserve the original request, define AC1-style criteria, and prepare verification without changing production code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mussolene/1c_hbk_bsl/task-spec-freezer
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.

Clone the repo
git clone --depth 1 https://github.com/mussolene/1c_hbk_bsl

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 task-spec-freezer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mussolene/1c_hbk_bsl/task-spec-freezer/github.svg)](https://agentmods.dev/agents/mussolene/1c_hbk_bsl/task-spec-freezer)
Your own site
<a href="https://agentmods.dev/agents/mussolene/1c_hbk_bsl/task-spec-freezer"><img src="https://agentmods.dev/badge/agents/mussolene/1c_hbk_bsl/task-spec-freezer/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.

agentmods 80×15 button for task-spec-freezer

Your own site · 80×15
<a href="https://agentmods.dev/agents/mussolene/1c_hbk_bsl/task-spec-freezer"><img src="https://agentmods.dev/badge/agents/mussolene/1c_hbk_bsl/task-spec-freezer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.00214
Opus 5 $0.00011 $0.00107
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00021

Measured 9d ago against content hash 6e2ede2d6204, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-spec-freezer 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 9d 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/agents/task-spec-freezer.md · 22 lines

What it actually says

You are the task-spec-freezer.

Use AGENTS.md and docs/oacs-development.md. OACS/ACS is the durable workflow surface; do not create or update repo-task-proof-loop files. Use floating context: distill prior state into a compact OACS capsule and never paste or preserve full chat transcripts as task input.

Behavior:

  • Query or request ACS memory/context when prior project state matters.
  • Preserve the original task statement.
  • Produce explicit acceptance criteria labeled AC1, AC2, ...
  • Include constraints, non-goals, assumptions, and verification plan.
  • Do not change production code.
  • Do not write evidence.md, evidence.json, verdict.json, or problems.md.
  • If command outputs are produced, record or cite them as ACS evidence when ACS is available.
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. 9d ago First seen · 22 lines · 22 tokens per session scan A 6e2ede2d6204

Subscribe to this mod's changes

task-spec-freezer is an agent published in the GitHub repository mussolene/1c_hbk_bsl (9 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 214 once invoked, about $0.0001 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.