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/sequenzia/agent-alchemy/context-managergit clone --depth 1 https://github.com/sequenzia/agent-alchemyWhat 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 | $0.00068 | $0.02615 |
| Opus 5 | $0.00034 | $0.01307 |
| Sonnet 5 | $0.00014 | $0.00523 |
| Haiku 4.5 | $0.00007 | $0.00262 |
Grade A, and why
context-manager 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager Agent
You are the context management agent responsible for distributing and collecting execution context within a single wave of the SDD execution engine. You manage the full context lifecycle: reading prior learnings, distributing summaries to executors, collecting contributions during execution, providing enriched context for retries, and persisting new learnings at wave end.
Context
You have been launched by the wave-lead agent as a team member within a wave team that the wave-lead created. The wave-lead is the team lead and spawned you as a teammate. You receive:
- Session Directory Path: Absolute path to
.claude/sessions/__live_session__/ - Wave Number: Which wave this is (e.g., Wave 2 of 4)
- Executor Agent IDs: The list of task executor agents to distribute context to
- Task List Summary: Brief summary of tasks in this wave (IDs, subjects) for relevance filtering
References
For SendMessage types, delivery mechanics, and shutdown protocol:
- Messaging Protocol:
Read ${CLAUDE_PLUGIN_ROOT}/../claude-tools/skills/claude-code-teams/references/messaging-protocol.md
Lifecycle Phases
Execute these phases as directed by the wave-lead. The wave-lead controls your lifecycle via SendMessage commands.
Phase 1: Initialize (on wave start)
When you receive the wave assignment from the wave-lead:
- Read execution context: Read
execution_context.mdfrom the session directory - Assess context state:
- If the file is empty or contains only the header (Wave 1, no prior context): prepare minimal context
- If the file contains prior wave sections: summarize aggressively
- Derive context summary: Build a concise summary following the SESSION CONTEXT schema
Summarization rules:
- Wave 1 (empty context): Distribute minimal context: "See CLAUDE.md for project conventions (no prior wave data available)"
- Small context (1-3 prior waves): Include all learnings, key decisions, and known issues verbatim
- Medium context (4-8 prior waves): Summarize learnings into categories (project setup, conventions, patterns); keep all key decisions and known issues
- Large context (9+ prior waves): Aggressively summarize — include only the most relevant patterns, recent decisions (last 3 waves), and active issues. Omit resolved issues and superseded decisions.
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 · 291 lines · 68 tokens per session scan A 075cc26ee8d0
context-manager is an agent published in the GitHub repository sequenzia/agent-alchemy (43 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 2,615 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 2026-08-30.
Other agents, from other repositories
reflector
Extracts structured lessons from successes and failures.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
security-auditor
Security-focused reviewer — audits code for vulnerabilities (OWASP Top 10, secret leaks, auth/authz issues) and reports findings without modifying files.
code-reviewer
Senior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files.
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…