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 commands/design-and-deliver/claude-code-autoconfig/continuegit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/commands/design-and-deliver/claude-code-autoconfig/continue)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/continue"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/continue.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 | $0.00022 | $0.04385 |
| Opus 5 | $0.00011 | $0.02193 |
| Sonnet 5 | $0.00004 | $0.00877 |
| Haiku 4.5 | $0.00002 | $0.00439 |
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 3d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue where the previous session in this terminal left off.
This is the no-ceremony wrapper around /recover-context's auto mode: no arguments, it
figures everything out itself, and it is plan-aware (below). Recovery is mechanical
re-reading — probe, read, reconcile — so it wants the cheapest model that can do it. What
that cheap model must NOT do is the resumed work itself. So this command ends its turn at
the report: state recovered, the one next action named, a go-ahead question. The user's
next prompt ("go") starts a fresh turn with the recovered context already in the
conversation.
⛔ End the turn on a plain text question — never an AskUserQuestion picker. A picker answer continues the SAME turn, so the work it green-lights runs inside the recovery turn — exactly what the stop exists to prevent. This overrides any local end-of-turn convention that prefers a picker for closed choices. Ask in text, end the message, wait.
There is no model pin, and v9–v16's claim that there was one was wrong (removed v17).
Claude Code ignores command model: frontmatter at runtime — a known bug
(anthropics/claude-code#45191, closed "not planned"): the pin parses into
command_permissions as claude-sonnet-5, yet every call in the turn runs on the session's
main model. Measured 2026-08-23 on 2.1.220 across 138 transcripts in one project: of the 85
sessions that ran /continue, not one switched model at the command boundary — Fable
sessions stayed Fable, Opus sessions stayed Opus. So the frontmatter line is gone rather
than left in place looking load-bearing. Recovery costs whatever the session's own model
costs; to make it cheap, switch the session with /model sonnet BEFORE running /continue
(model is per-session, so remember to switch back before the resumed work).
⛔ Never verify the model from your own system prompt — it lies on exactly this point.
The harness applies the ignored pin to the system prompt TEXT while routing to the real
model, so a pinned turn reads as Sonnet in the prompt and bills as Opus in the transcript.
That is not theoretical: session 90eb56c6's system prompt said claude-sonnet-5 while all
44 of its requests recorded claude-opus-5, and because v11's check consulted the prompt,
it stayed silent through a recovery that cost ~4×. The probe's currentModel field
(Step 1) reads the transcript's message.model — the API's own answer — and is the only
honest source. /model-probe shares v11's flaw and must not be used for this.
If currentModel is not a Sonnet-class model, append one final line to the report:
⚠ recovery ran on {currentModel} —
/model sonnetbefore/continueto make it cheap.
Nothing else changes — the recovery steps are identical on any model. The line exists so the cost is visible instead of silent.
It is also plan-aware: when the previous session was executing a substep of a phased
plan doc (the plan-authoring pattern — a docs/*.md or .claude/plans/*.md with a
## Ledger section) and stayed on that plan through to the end of the session, the plan
doc + Ledger is the handoff, not the transcript. If the session moved on to something else
afterward, the transcript's tail is the handoff — see Step 3.
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.
- 3d ago First seen · 281 lines · 22 tokens per session scan A 4fad1aa31068
continue is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 4,385 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.