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/bambooshadow-studio/mcp-power-packWrote 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/rules/bambooshadow-studio/mcp-power-pack/ai-context-management)<a href="https://agentmods.dev/rules/bambooshadow-studio/mcp-power-pack/ai-context-management"><img src="https://agentmods.dev/badge/rules/bambooshadow-studio/mcp-power-pack/ai-context-management.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 5.1 | $0.00241 | $0.00241 |
| Opus 5 | $0.00120 | $0.00120 |
| Sonnet 5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
ai-context-management 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 7d 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
Rule Name: ai-context-management Description: When the conversation context is getting long or the model is losing track of details, proactively summarize and restructure context.
// CONTEXT MANAGEMENT
When to Summarize
- After 10+ file modifications in a session
- When the model starts repeating itself or forgetting details
- Before starting a significantly different task
- When approaching context limits
What to Preserve in Summary
- Project goals and current milestone
- Architecture decisions made
- Files created/modified and their purposes
- Known issues or limitations
- Next steps
Context Structure
## Session Summary
**Goal:** [current task objective]
**Status:** [in progress / blocked / complete]
### Files Changed
- [path]: [what was done]
### Decisions
- [decision]: [rationale]
### Blockers
- [issue]: [what's needed]
### Next
1. [next action item]
2. [next action item]
Best Practices
- Keep summaries under 500 tokens
- Only include decisions that affect future work
- Remove resolved issues from context
- Link to specific file paths and line numbers
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.
- 7d ago First seen · 44 lines · 241 tokens per session scan A a9dae89dfe64
ai-context-management is a cursor rule published in the GitHub repository bambooshadow-studio/mcp-power-pack (1 stars, last pushed 2mo ago), licensed MIT. It adds 241 tokens to every session, about $0.0012 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 cursor rules, from other repositories
repo-context-ledger
Route Cursor through the repository's verified, cross-Agent context ledger.
nauro-adopt
Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
replen
Replen integration — session-start matches, portfolio recall, silent auto-reground.
cursor-brain-os
Brain OS operating instructions — use MCP tools for project state, not source-code grep.
workflow-memory
Workflow memory operating loop — read root state before acting, write state back after meaningful change.