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/stefan-jansen/coding-agent-toolkit/continuenpx skills add stefan-jansen/coding-agent-toolkit --skill continuegit clone --depth 1 https://github.com/stefan-jansen/coding-agent-toolkitWhat 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 | $0.00074 | $0.01956 |
| Opus 5 | $0.00037 | $0.00978 |
| Sonnet 5 | $0.00015 | $0.00391 |
| Haiku 4.5 | $0.00007 | $0.00196 |
Grade B, and why
continue scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
parsed sections but do not actually run any commands. Useful when the How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
continue — resume from a transition file
You are running the CONTINUE step of the workflow. Your job is
to take a transition file produced by /handoff (or a freeform digest of
the same shape) and bring the current session up to the state described
there: confirm the working directory, run the verification snapshot, flag
any drift against expected values, and present the suggested next steps so
the user (or you) can pick one.
This step is host-neutral: same contract on Claude and Codex. The
shared .workspace/transitions/ tree is the cross-host primitive — any
session on either host can resume any transition file.
/continue is read + verify + present. It does NOT auto-execute a
suggested next step — picking one is the user's call (or yours, after
presenting the options).
Arguments
Parse these from the user's invocation (any order):
| Arg | Required | Default | Meaning |
|---|---|---|---|
--from <path> |
no | most recently modified file under .workspace/transitions/ |
Transition file to resume |
--verify |
no | true | Run the verification snapshot and report drift |
--no-verify |
no | false | Skip verification; only read + present |
--cwd <path> |
no | the one named in the file's "Working directory" section | Override the cwd for verification |
If the user pastes continue from <path> as the prompt itself, treat
<path> as --from. This is the canonical "resumption" phrase that
/handoff's output footer produces — recognizing it is part of the
contract.
Resolving --from
If --from is omitted:
- Walk
.workspace/transitions/(newest dated subdirectory first). - Pick the most recently modified
.mdfile. - If there are multiple files in the same minute, pick the
alphabetically last (highest
HHMMSS). - If
.workspace/transitions/is empty or missing → abort with a suggestion to run/handofffirst or to specify--fromexplicitly.
If the path doesn't exist → abort with the path the user named, and
suggest ls .workspace/transitions/$(date -u +%Y-%m-%d)/.
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 · 205 lines · 74 tokens per session scan B e0a76f025eb8
continue is a skill published in the GitHub repository stefan-jansen/coding-agent-toolkit (22 stars, last pushed 17d ago), licensed MIT. It adds 74 tokens to every session and 1,956 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…