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/ohong/agent-skills/continuenpx skills add ohong/agent-skills --skill continuegit clone --depth 1 https://github.com/ohong/agent-skillsWhat 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 | $0.00045 | $0.00614 |
| Opus 5 | $0.00023 | $0.00307 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
continue 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission Continue — Forced Reorientation
Context refresh is not a limitation — it's Boyd's reorientation in action.
You are resuming a mission with fresh context. This is the most powerful moment in the OODA cycle: your old context, with its accumulated drift, stale assumptions, and lost-in-the-middle effects, is gone. You start clean. The .mission/ files carry your shared orientation forward.
Reorientation procedure
1. Observe — Read the state from disk
Read these files in order (background first, current task last — recency anchoring):
.mission/plan.md— the full plan (shared intent).mission/learnings.md— if it exists, patterns from earlier work (shared experience).mission/progress.md— current state (shared situation awareness) — read this last so it's freshest in context
If .mission/plan.md doesn't exist: "No mission plan found. Run /mission:plan <task> first." Stop.
2. Orient — Build your mental model
From the files, identify:
- Which milestones are completed (
[x]) - Which milestone is next (first
[ ]or[>]) - Any notes about blockers, partial work, or discoveries
- The acceptance criteria for the next milestone
3. Announce — Confirm orientation
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MISSION RESUMED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Completed: {N}/{total} milestones
Resuming: Milestone {N+1}: {title}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
4. Mismatch check
If progress notes mention partially completed work:
- Read the relevant source files from disk
- Run a quick verification — does the current state match what progress.md claims?
- If there's a mismatch between progress notes and actual file state, trust the FILES. Update progress.md to reflect reality.
5. Execute — Enter the OODA cycle
Follow the execution protocol in ../../references/execution-protocol.md starting from the next incomplete milestone.
The principle
You have fresh context. This is an advantage, not a handicap. You don't carry forward stale assumptions, accumulated drift, or mid-context attention degradation. You start with a clean orientation built from ground truth (the files).
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 · 68 lines · 45 tokens per session scan A 48f15e8a5195
continue is a skill published in the GitHub repository ohong/agent-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 614 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
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…