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 apex-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/apex-context-management)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-context-management"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-context-management/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/skills/jonathan-vella/apex-accelerator/apex-context-management"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-context-management.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 | $0.00103 | $0.01490 |
| Opus 5.5 | $0.00041 | $0.00596 |
| Sonnet 5 | $0.00021 | $0.00298 |
| Haiku 4.5 | $0.00010 | $0.00149 |
Grade A, and why
apex-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 today.
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 — 151 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 compact decisions; retain required safety evidence losslessly |
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 prefer the minimal artifact tier.
Required missing guidance and safety evidence must still be recovered.
These are repository trip-wires, not verified model API limits; use the
active harness limit when known and do not infer it from a model name.
Full per-model table, checkpoint procedure, 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
What ships with it
11 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/context-audit.md 2.5 KB
- references/debug-log-export.md 21 KB
- references/hard-checkpoints.md 2.9 KB
- references/log-profiling.md 5.5 KB
- references/skill-loading.md 846 B
- references/token-estimation.md 3.7 KB
- scripts/parse-chat-logs.py 8.1 KB runs code
- templates/optimization-report.md 3.4 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.
- today First seen · 151 lines · 103 tokens per session scan A 14cdf7a1ed67
apex-context-management is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,490 once invoked, about $0.0004 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 2026-09-23.
Other skills, from other repositories
inspect-history
Investigate prior AI coding activity, commands, tool outcomes, files, sessions, and tests for an active continuity task without changing project files.
resume-task
Resume an in-progress coding task previously worked on by this or another AI agent using captured local context, Git state, test history, and checkpoints.
honcho-memory
Query the Honcho persistent memory store for facts about peers (users or agents). Use this for any "what do you know about me / the user" style question instead of fabricating from training data.
meditation
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory.
token-waste-elimination
Audit and eliminate token waste from cognitive architecture memory files -- instructions, prompts, skills, and agents.
tiered-memory
Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn.