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 skills/aget-framework/aget/aget-open-sessionnpx skills add aget-framework/aget --skill aget-open-sessiongit clone --depth 1 https://github.com/aget-framework/agetWrote 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/aget-framework/aget/aget-open-session)<a href="https://agentmods.dev/skills/aget-framework/aget/aget-open-session"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-open-session.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 | $0.00034 | $0.01372 |
| Opus 5 | $0.00017 | $0.00686 |
| Sonnet 5 | $0.00007 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
aget-open-session 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- aget-open-session — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aget-open-session
Open a session with context-aware establishment. Orchestrates wake-up, then adds context recovery, health gating, and session provenance.
Purpose
The current /aget-wake-up skill runs wake_up.py and displays agent identity — but leaves context recovery to the principal. Open-session transforms session initialization from identity display into context-aware session establishment by adding: prior session context recovery, pre-session health gating, and opened_by provenance (mirroring closed_by from SP-008).
Evidence: SP-008 (close-session) validated composition architecture with cross-fleet evidence (8 sessions). L562 (rename caused 32/32 false-positive drift) confirms composition over rename. L335 (Memory Architecture) specifies 2-minute context recovery target. L670 (Session Quality Assessment Gap). Principal confirmed open/close verb pair (2026-04-10) over start/stop and init/close alternatives.
Input
$ARGUMENTS (none required)
Examples:
/aget-open-session— Full open with context recoveryopen session— Natural language triggeropen this session— Natural language trigger
Execution
Phase 1: Wake-Up Delegation
Run wake-up infrastructure as a single Bash call:
Run the wake-up script using the agent's canonical path:
# Try canonical paths in order (agents may have different locations)
if test -f scripts/wake_up.py; then
python3 scripts/wake_up.py
elif test -f .aget/patterns/session/wake_up.py; then
python3 .aget/patterns/session/wake_up.py
else
echo "No wake_up.py found — run manual wake-up"
fi
Optionally log invocation if telemetry script available:
test -f scripts/log_skill_invocation.py && python3 scripts/log_skill_invocation.py --skill aget-open-session --version 0.1.0 --outcome success --duration-seconds 0
This produces agent identity, version, git status, and health check.
Phase 2: Context Recovery
Using Read, Grep, and Glob (no Bash — zero permission cost):
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.
- 5d ago First seen · 128 lines · 34 tokens per session scan A 9d93dd26e19d
aget-open-session is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,372 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 2026-08-30.
Other skills, from other repositories
aget-open-session
Open a session with context-aware establishment. Orchestrates wake-up, recovers prior session context, surfaces pending work, and proposes a session agenda.
aget-record-lesson
Record lessons learned from sessions as persistent, searchable, committable artifacts. Classifies each lesson as Framework (help other AGETs) or Domain (help principal).
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
memory-consolidation
Use when consolidating session signals into curated memory — four-phase loop ORIENT → GATHER → CONSOLIDATE → PRUNE. Triggers on 'mine my sessions', 'consolidate memory', 'review intake signals'.
design-system-capture
Write and maintain DESIGN.md + PRODUCT.md — captures visual decisions and interaction patterns so design tasks stay consistent across sessions without re-scanning past work.
cordis-plugin-sofagent-evolve
经验沉淀——think.md 反思 + Dream Cycle + skillopt + instinct→skill + refine（seam: 任务结束 hook）——桥接 @sofagent/think generateThinkEntry（sofagent 品牌插件 · 主色 #16B8F3）——DSH（DeepSeek Harness）cordis plugin。sofagent 约束层在 DeepSeek Harness 生态的插件形态。.