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 skills add jonathan-vella/apex-accelerator --skill context-managementgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/skills/jonathan-vella/apex-accelerator/context-management)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/context-management"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/context-management.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.01287 |
| Opus 5 | $0.00051 | $0.00643 |
| Sonnet 5 | $0.00020 | $0.00257 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Management Skill
Unified context-window management with two distinct lifecycles:
- Runtime Compression — what an agent does before loading a large artifact to stay under the model context limit (during workflow execution).
- Diagnostic Audit — what the 11-Context Optimizer agent does after the fact to find waste in agent definitions, instructions, and skill loads.
The two modes do not depend on each other — pick the section that matches your need.
Mode A: Runtime Compression
Replaces the legacy
context-shreddingskill.
When to Use Runtime Compression
- Before loading a predecessor artifact file (01 through 07)
- When conversation length suggests >60% of model context is used
- When an agent needs to load multiple large artifacts
Compression Tiers
| Tier | Context Usage | Strategy |
|---|---|---|
full |
< 60% | Load entire artifact — no compression |
summarized |
60-80% | Load key H2 sections only |
minimal |
> 80% | Load decision summaries only (< 500 chars) |
Hard Token Checkpoints
Percentages are advisory; absolute input-token counts override them.
GPT-5.6-Terra and Luna hard-checkpoints at ≥300K input; Claude Opus 5 at ≥160K. When
hit, emit a compaction message and switch every further read to the
minimal tier. Full per-model table, checkpoint procedure (4 steps), and
background context (nordic-foods saturation event) in
references/hard-checkpoints.md.
Rules
- Estimate context usage — count approximate conversation tokens
- Select tier based on the thresholds above
- Apply compression template from
references/compression-templates.md - If loading multiple artifacts, compress the older / less-critical ones first
Steps
1. Estimate current context usage (rough: 1 token ≈ 4 chars)
2. Check model limit (Claude family: 200K, GPT-5 family: 400K)
3. Calculate usage percentage and check hard-checkpoint table
4. Select tier:
< 60% → full (no compression needed)
60-80% → summarized (key sections only)
> 80% → minimal (decision summaries only)
5. Load artifact/skill using the appropriate variant
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/analysis-methodology.md 8.5 KB
- references/audit-setup.md 2.0 KB
- references/compression-templates.md 6.6 KB
- references/hard-checkpoints.md 2.6 KB
- references/log-profiling.md 3.9 KB
- references/skill-loading.md 734 B
- references/token-estimation.md 4.2 KB
- scripts/parse-chat-logs.py 8.1 KB runs code
- templates/optimization-report.md 3.3 KB
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.
- 4d ago First seen · 134 lines · 101 tokens per session scan A be649ba39e41
context-management is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed today), licensed MIT. It adds 101 tokens to every session and 1,287 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
fuzzy-selecting
Use when choosing interactively from search results, files, processes, or any command output with preview capabilities.
searching-text
Use when searching for text patterns across files, finding specific code locations, or getting lines with surrounding context in a single call.
replacing-text
Use when performing text find & replace, batch transformations across files, or when JavaScript-style regex syntax is preferred over sed.
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
deep-work-optimization
Focus blocks, distraction management, and flow state triggers for cognitively demanding work.
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.