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 ihabkhaled/AI-Psychiatry --skill context-compressiongit clone --depth 1 https://github.com/ihabkhaled/AI-PsychiatryWrote 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/ihabkhaled/ai-psychiatry/context-compression)<a href="https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/context-compression"><img src="https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/context-compression.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 | $0.00031 | $0.00210 |
| Opus 5 | $0.00015 | $0.00105 |
| Sonnet 5 | $0.00006 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
context-compression 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 8d 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
Context Compression
Core principle
Preserve actionable truth; drop raw reasoning, abandoned speculation, duplicate output, and outdated hypotheses.
Procedure
- Capture Goal, Completed, Remaining, Decisions, Evidence, Blocker, Deferred, and Next action.
- Keep exact errors, counts, paths, and commands only when material.
- Remove repeated explanations and obsolete hypotheses.
- Separate temporary state from durable knowledge.
- Validate important facts against current source.
- Write the compact state to the task context.
Required output
A short structured resume record with the eight required fields.
Limits
Use the smallest state that supports reliable continuation.
Common mistakes
Do not store chain-of-thought, giant logs, or promote temporary debugging to memory.
Stop condition
Stop when a future agent can resume without rereading the whole repository.
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.
- 8d ago First seen · 37 lines · 31 tokens per session scan A 5b4ba1b9a33e
context-compression is a skill published in the GitHub repository ihabkhaled/AI-Psychiatry (3 stars, last pushed 23d ago), licensed MIT. It adds 31 tokens to every session and 210 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 skills, from other repositories
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
context-budget
Use when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must preserve, and whether to isolate a read-heavy subtask in a subagent. NOT dollar spend or caps (that is cost-tracking), NOT finding context…
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
self-improvement
Captures lessons and promotes recurring patterns.
evolve
Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.
memory-cleanup
Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under /.claude/projects//memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke…