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/tk-logl/sentinel/memory-guardnpx skills add tk-logl/sentinel --skill memory-guardgit clone --depth 1 https://github.com/tk-logl/sentinelWhat 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 | $0.00029 | $0.01213 |
| Opus 5 | $0.00015 | $0.00607 |
| Sonnet 5 | $0.00006 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
memory-guard 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 2d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Guard — Context Preservation System
Prevents information loss during context compaction, session switches, and /clear commands.
The Problem
AI assistants lose context when:
- Context compaction — the system summarizes old messages to fit the window
- Session end — user runs /clear or closes the session
- Session crash — unexpected termination
- Long tasks — context fills up during extended work
Lost information includes: current task, decisions made, files being edited, error patterns, and next steps.
The Solution: 5-Section Structured State
Every state save captures five sections:
1. Session Intent
What you're working on and why. Includes the task_id if one exists.
2. Modified Files
All files with uncommitted changes, plus a diff summary.
3. Decisions Made
Rationale for choices made during the session, including rejected alternatives. This is the most valuable section — it prevents re-debating the same decisions.
4. Current State
Git status, recent commits, recent errors, and any blockers.
5. Next Steps
What was in progress when the save happened, and what should come next.
How State is Saved
Automatic (hooks handle this)
| Event | Hook | Location |
|---|---|---|
| Context compaction | state-preserve.sh (PreCompact) |
.sentinel/state/latest.md + timestamped archive |
| Session end / /clear | session-save.sh (SessionEnd) |
.sentinel/state/latest.md + timestamped archive |
| Session start | session-init.sh (SessionStart) |
Re-injects .sentinel/state/latest.md into context |
Manual
You can also save state manually at any time:
Write the 5-section state to .sentinel/state/latest.md
Recovery Chain
When a session starts, recovery follows this priority chain:
1. .sentinel/state/latest.md ← Most recent structured state
2. .sentinel/current-task.json ← Active task context
3. .sentinel/error-log.jsonl ← Recent error patterns
4. git log --oneline -5 ← Recent commits (always available)
5. git status ← Uncommitted work (always available)
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.
- 2d ago First seen · 147 lines · 29 tokens per session scan A 8ab925d3c152
memory-guard is a skill published in the GitHub repository tk-logl/sentinel (4 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,213 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…