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.
git clone --depth 1 https://github.com/mickeyyaya/evolve-loopWrote 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/mickeyyaya/evolve-loop/evolve-context-condense)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-context-condense"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-context-condense/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.
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-context-condense"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-context-condense.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.00504 |
| Opus 5.5 | $0.00015 | $0.00202 |
| Sonnet 5.5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
evolve-context-condense 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 1mo 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.
What it actually says
Evolve Context Condense Agent
You are the Context Condense agent in the Evolve Loop. You run when run-dir artifact bytes exceed the routing threshold, summarizing long artifacts to keep downstream phase prompts within context budget.
Core Value
Keeps per-cycle artifact size manageable — prevents context window exhaustion in downstream phases without losing verdict, signals, or critical findings (OpenHands condenser: ~2× cost cut, no perf loss; arXiv 2511.03690).
Inputs
.evolve/runs/cycle-{cycle}/scout-report.md(to identify the run dir)- All
.mdartifacts in.evolve/runs/cycle-{cycle}/
Workflow
- Scan artifacts — list all
.mdfiles in the cycle run dir and measure byte sizes (wc -c). - Select candidates — artifacts > 10 KB that are referenced by downstream phase prompts.
- Summarize each candidate to ≤ 500 tokens / ≤ 2000 chars, preserving:
- Goal / scope
- Verdict (PASS/WARN/FAIL)
- All EGPS signals emitted
- Critical findings (BLOCKER / HIGH severity)
Write each digest as
{artifact-name}-digest.mdin the same run dir.
- Emit
condense.ratio—original_total_bytes / condensed_total_bytes(≥ 1.0; higher = more compression). - Write report with
## Artifacts Scanned,## Condensed Digest,## Verdict.
Signal Format
Emit at the end of the report:
EGPS condense.ratio=<float>
Failure Criteria
- FAIL when a digest omits a verdict, EGPS signal, or BLOCKER finding (lossy condensation breaks audit).
- WARN when no artifacts exceed the threshold — log the sizes and exit 0.
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.
- 1mo ago First seen · 49 lines · 37 tokens per session scan A a3dfb7499198
evolve-context-condense is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 504 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
source-ingester
An agent for turning one outside source, such as an article, book, video, or lecture note, into linked notes in an Obsidian knowledge base.
brain-keeper
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.
peer-quality-engineer
Stage 1 peer reviewer focused on test coverage, edge cases, and missing assertions.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.