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/mracal/vibe-engineering/session-context-flushnpx skills add mracal/vibe-engineering --skill session-context-flushgit clone --depth 1 https://github.com/mracal/vibe-engineeringWrote 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/mracal/vibe-engineering/session-context-flush)<a href="https://agentmods.dev/skills/mracal/vibe-engineering/session-context-flush"><img src="https://agentmods.dev/badge/skills/mracal/vibe-engineering/session-context-flush.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 | $0.00038 | $0.00481 |
| Opus 5 | $0.00019 | $0.00241 |
| Sonnet 5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
vibe-session-context-flush 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.
This is a copy
100% identical to vibe-session-context-flush — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
vibe-session-context-flush
Context windows have limits. This skill manages the transition gracefully instead of letting context degrade silently.
When to Use This Skill
- You notice responses getting less coherent or losing track of earlier context
- You've been working for a long session with many file reads
- The system indicates context compression is occurring
- Before starting a new major subtask in a long session
When NOT to Use This Skill
- Short sessions with plenty of context room
- When the user wants to continue without interruption
- When you just started the session
Steps
-
Assess current context — What's consuming context?
- Large file reads that are no longer relevant
- Completed subtask details that can be summarized
- Exploration results that led to dead ends
- Verbose tool outputs
-
Triage into:
- Keep — Still actively needed (current task state, open files, error messages)
- Summarize — Completed work (compress to 2-3 sentences each)
- Drop — No longer relevant (old file contents, superseded plans)
-
Create compact state:
## Session State (Flushed) **Current task**: [what we're doing] **Branch**: [current branch] **Modified files**: [list] **Completed**: [summary of done work] **Key decisions**: [1-liner each] **Next step**: [immediate next action] **Important context**: [anything that must be preserved] -
Offer to the user — "Context is getting large. Here's a compact state. Want me to continue with this summary, or start a new session with the handover doc?"
Output Format
Context Flush Summary
Context pressure: High / Medium Items summarized: X Items dropped: Y
[Compact state block as above]
Recommendation: Continue with summary / Start new session with /vibe-handover-doc
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 · 62 lines · 38 tokens per session scan A b84168a95a4e
vibe-session-context-flush is a skill published in the GitHub repository mracal/vibe-engineering (3 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 481 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to vibe-session-context-flush, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
handover
Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".
do-it-context
Use when repo terms or invariants are drifting, or when user/docs/code naming disagrees and a canonical glossary is needed — .do-it/CONTEXT.md is the downstream source of truth for names, relationships, and facts.
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
deploy
Use when shipping a release of Agent Sessions — bumping version, updating CHANGELOG, building, signing, notarizing, publishing appcast, and creating a GitHub release.