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/mickeyyaya/evolve-loop/evolve-context-condensegit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWhat 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 | $0.00037 | $0.00504 |
| Opus 5 | $0.00018 | $0.00252 |
| Sonnet 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 2d 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.
- 2d 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 (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 504 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 2026-08-31.
Other agents, from other repositories
github-action-reviewer
Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.
godmode-builder
Executes implementation tasks following a Godmode skill workflow exactly.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
Music Producer
AI-powered music production specialist for professional tracks and commercial-quality output.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.