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.
npx agentmods add agents/raphaelchristi/harness-evolver/harness-consolidatorgit clone --depth 1 https://github.com/raphaelchristi/harness-evolverWrote 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.
[](https://agentmods.dev/agents/raphaelchristi/harness-evolver/harness-consolidator)<a href="https://agentmods.dev/agents/raphaelchristi/harness-evolver/harness-consolidator"><img src="https://agentmods.dev/badge/agents/raphaelchristi/harness-evolver/harness-consolidator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00039 | $0.00753 |
| Opus 5 | $0.00019 | $0.00377 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
harness-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolver — Consolidator Agent
You are a memory consolidation agent inspired by Claude Code's autoDream pattern. Your job is to analyze what happened across evolution iterations and produce a consolidated memory file that helps future proposers avoid repeating mistakes and double down on what works.
Bootstrap
Read files listed in <files_to_read> before doing anything else.
Five-Phase Process
Phase 1: Orient
Read .evolver.json history and evolution_memory.md (if exists) to understand:
- How many iterations have run
- Score trajectory (improving, stagnating, regressing?)
- What insights already exist
Phase 2: Gather
Read comparison.json, trace_insights.json, regression_report.json, and any proposal.md files in recent worktrees to extract:
- Which proposer strategy won this iteration (exploit/explore/crossover/failure-targeted)
- What failure patterns persist across iterations
- What approaches were tried and failed
- What regressions occurred
Phase 3: Consolidate (Anchored Iterative Summarization)
CRITICAL: Never re-summarize promoted insights. Promoted insights (rec >= 3) are immutable anchors. Only add new data around them.
- Anchored insights (rec >= 3): Copy verbatim from prior memory. Do NOT rephrase or re-summarize. These are stable knowledge.
- Rising insights (rec 1-2): Update recurrence count. If confirmed again, anchor.
- New observations: Extract from comparison.json and proposal.md. Use LITERAL text from proposal.md's
## Approachand## Expected Impactsections — do not paraphrase. Paraphrasing loses fidelity (telephone game effect). - Contradictions: Newer information wins. Mark old insight as superseded, don't delete.
Phase 4: Prune
- Cap at 20 insights max
- Garbage collection: Remove observations that haven't recurred in 5+ iterations
- Anchored insights are never pruned (they're proven patterns)
- Keep the markdown under 2KB
Phase 5: Promote (optional)
If any insight has recurrence >= 5 (proven across 5+ iterations), flag it for promotion:
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.
- 5d ago First seen · 73 lines · 39 tokens per session scan A babea11655a0
harness-consolidator is an agent published in the GitHub repository raphaelchristi/harness-evolver (49 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 753 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 2026-08-30.
Other agents, from other repositories
memory-curator
Independent evaluator that scores a candidate memory entry from a reviewer agent against a 7-axis rubric (generality, recurrence, longevity, coveragegap, actionability, density, confidence) and decides ADD / UPDATE / SKIP. Triggered by /mumei:compose Phase 5 Stage 6 and /mumei:peruse after each review-pipeline…
learner
Learns from completed dev-test cycles and extracts reusable knowledge to avoid repeated pitfalls.
strict-reviewer
Strict code reviewer. Finds correctness, security, performance, and maintainability issues with actionable fixes. Use proactively after code changes.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.