meta-harness-proteus

meta-harness-proteus is a skill for Claude Code from 001TMF/harness-forge. It costs 24 tokens per session (822 once invoked), scanned A, original, MIT.

A tool for developing short summaries of records used by the Proteus memory system. It tests ways to preserve important facts about past work while using fewer characters in the summary.

In plain words
What is it for?
Use it to prototype and compare memory-summary compressors for Proteus. It creates candidate compressors for an external evaluation process rather than running the benchmarks itself.
Why use it?
It helps reduce the amount of context added to an agent while retaining details such as the target, approach, result, quality, difficulty, and lessons for future tasks.

Skill for Claude Code

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

Good fit Use it to prototype and compare memory-summary compressors for Proteus. It creates candidate compressors for an external evaluation process rather than running the benchmarks itself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/001tmf/harness-forge/meta-harness-proteus
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.

Any agent
npx skills add 001TMF/harness-forge --skill meta-harness-proteus
Clone the repo
git clone --depth 1 https://github.com/001TMF/harness-forge

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 meta-harness-proteus

README.md
[![agentmods](https://agentmods.dev/badge/skills/001tmf/harness-forge/meta-harness-proteus/github.svg)](https://agentmods.dev/skills/001tmf/harness-forge/meta-harness-proteus)
Your own site
<a href="https://agentmods.dev/skills/001tmf/harness-forge/meta-harness-proteus"><img src="https://agentmods.dev/badge/skills/001tmf/harness-forge/meta-harness-proteus/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 meta-harness-proteus

Your own site · 80×15
<a href="https://agentmods.dev/skills/001tmf/harness-forge/meta-harness-proteus"><img src="https://agentmods.dev/badge/skills/001tmf/harness-forge/meta-harness-proteus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 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 $0.00024 $0.00822
Opus 5 $0.00012 $0.00411
Sonnet 5 $0.00005 $0.00164
Haiku 4.5 $0.00002 $0.00082

Measured 9d ago against content hash 87f42a3d44d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

meta-harness-proteus 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

examples/memory-summary/.claude/skills/meta-harness-proteus/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Harness — proteus memory-summary evolution

Run ONE iteration. Do all work in the main session — do NOT delegate to subagents.

You do NOT run benchmarks. You analyze prior results, prototype a mechanism, and write new candidate summary compressors. The outer loop (meta_harness.py) scores them on (fidelity, chars) separately, with no model and no network.

What a candidate is

A summary compressor: it turns one campaign-memory record (a dict — see corpus.py) into the short string injected into the policy's context on retrieval. The proteus analog of a memory system. The grading is in corpus.py::score_fidelity: the fraction of load-bearing facts (target, surface, strategy, outcome, quality, difficulty, transfer hint) that survive in your summary. Context cost = len(summary).

The objective

Preserve fidelity (>= the floor in config.yaml, currently 0.70 worst-record) while using FEWER characters than agents/baseline_incumbent.py. The frontier is Pareto: fidelity up, chars down. You cannot win by dropping facts — a summary that loses a required fact loses fidelity and falls off the frontier.

CRITICAL CONSTRAINTS

  • Implement exactly 3 new compressors this iteration.
  • Each must change a mechanism, not a constant. Bad: "same template, drop the organism." Good ideas: abbreviation/symbol encoding of fixed vocab (surface types, outcomes); a key:value micro-syntax instead of prose; dropping only provably-redundant words; reordering so the highest-value facts survive truncation; field-name elision where the value is self-identifying.
  • No record-specific hints. Never hardcode a target name, campaign_id, or any value from corpus.py into a compressor. It must generalize to unseen records. (This is the anti-leakage rule — load-bearing for proteus.)
  • Do not abort early or write "the frontier is optimal".

Workflow

  1. Analyze. Read logs/evolution_summary.jsonl (what's been tried), logs/frontier.json (current best), corpus.py (records + rubric), agents/baseline_incumbent.py (the system to beat).
  2. Prototype (mandatory). Write a throwaway script in /tmp/ that runs your compression idea over a couple of corpus.py records and checks fidelity by eye before committing. Delete it after.
  3. Implement. For each of 3 candidates: copy agents/baseline_incumbent.py to agents/<snake_name>.py, subclass SummaryCompressor, implement summarize(self, record) -> str. Import from candidate_base. Self-critique: is this a new mechanism or just a tweaked constant? If the latter, rewrite.
  4. Validate. python -c "import agents.<name>; print('OK')" from the repo root.
  5. Write logs/pending_eval.json:

Read the full file on GitHub · 78 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. 9d ago First seen · 78 lines · 24 tokens per session scan A 87f42a3d44d0

Subscribe to this mod's changes

meta-harness-proteus is a skill published in the GitHub repository 001TMF/harness-forge (78 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 822 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 2026-08-30.

Related

Other skills, from other repositories

knowledge_store_skill

Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…

NPC-Worldwide/npcpy · 346 tokens

cocoscout

Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.

Snowflake-Labs/cocoplus · 59 tokens

cocohealth

Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.

Snowflake-Labs/cocoplus · 38 tokens

pull-search

CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.

Snowflake-Labs/cocoplus · 38 tokens

pod-kb

Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.

Snowflake-Labs/cocoplus · 33 tokens

pod-resume

Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.

Snowflake-Labs/cocoplus · 50 tokens