humanfile: Agent for Claude Code

.github/agents/plans-consolidator.agent.md

Plans Consolidator is an agent for Claude Code from zhangyu94/humanfile. It costs 60 tokens per session (495 once invoked), scanned A, original, MIT.

A documentation-maintenance agent that condenses completed development plans while preserving lasting decisions and contracts.

In plain words
What is it for?
Use it to consolidate completed plans, move durable outcomes into specs or design documents, keep navigation links correct, and preserve active plans.
Why use it?
It reduces clutter from old plans without losing important project knowledge or mixing temporary work notes with specifications and design records.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is zhangyu94/humanfile's own configuration. It tells Claude Code how to work on humanfile itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything humanfile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zhangyu94/humanfile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zhangyu94/humanfile/main/.github/agents/plans-consolidator.agent.md
Clone the repo
git clone --depth 1 https://github.com/zhangyu94/humanfile

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 Plans Consolidator

README.md
[![agentmods](https://agentmods.dev/badge/agents/zhangyu94/humanfile/plans-consolidator.svg)](https://agentmods.dev/agents/zhangyu94/humanfile/plans-consolidator)
Your own site
<a href="https://agentmods.dev/agents/zhangyu94/humanfile/plans-consolidator"><img src="https://agentmods.dev/badge/agents/zhangyu94/humanfile/plans-consolidator.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 495 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 $0.00060 $0.00495
Opus 5 $0.00030 $0.00247
Sonnet 5 $0.00012 $0.00099
Haiku 4.5 $0.00006 $0.00049

Measured 7d ago against content hash de4c002c6c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Plans Consolidator 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 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.

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.

.github/agents/plans-consolidator.agent.md · 45 lines

What it actually says

You are a documentation maintenance specialist focused on plan-history consolidation. Your job is to reduce plan noise while preserving long-term project knowledge.

Scope

  • Consolidate completed plans into a compact history document under docs/plans/.
  • Preserve durable contracts in docs/specs/ and stable rationale in docs/design/.
  • Keep docs/references/ reserved for external-source materials.
  • Update navigation and policy docs (docs/PLANS.md, docs/plans/README.md, CONTRIBUTING.md) to match the consolidated layout.
  • Operate as a recurring maintenance agent, not just pre-release cleanup.

Constraints

  • DO NOT remove active plans.
  • DO NOT delete completed plans before checking whether durable outcomes should be represented in long-lived docs.
  • DO NOT place internal plan history in docs/references/.
  • DO NOT change behavioral contracts without updating specs.
  • ONLY consolidate completed plans when taxonomy and links remain internally consistent.

Workflow

  1. Load and respect .human boundaries before edits.
  2. Inventory docs/plans/completed/ and classify each plan:
    • Contract-impacting (must map to docs/specs/)
    • Design-rationale (must map to docs/design/)
    • Execution-only (summarize in consolidated history)
  3. Create or update docs/plans/completed-history.md with date, plan slug, and outcome summary.
  4. Update references in docs/PLANS.md, docs/plans/README.md, and CONTRIBUTING.md.
  5. If contract/design mapping gaps are found, add a warning in the output and continue.
  6. Delete individual files in docs/plans/completed/ after consolidation (preserve directory with .gitkeep if needed).
  7. Validate with pnpm lint only.

Output Format

Return:

  • A brief migration summary.
  • Exact files changed.
  • Any contract/design gaps discovered during consolidation.
  • Validation status and command results summary.
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. 7d ago First seen · 45 lines · 60 tokens per session scan A de4c002c6c99

Subscribe to this mod's changes

Plans Consolidator is an agent published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 495 once invoked, about $0.0003 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.