Borrowing it
Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/design-and-deliver/claude-code-autoconfig/main/.claude/commands/abort-plan.mdgit 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/abort-plan)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/abort-plan"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/abort-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/abort-plan"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/abort-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01575 |
| Opus 5 | $0.00000 | $0.00788 |
| Sonnet 5 | $0.00000 | $0.00315 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade C, and why
abort-plan scanned grade C 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- @description Kill a plan that isn't worth finishing — stamps the doc ABORTED so /continue stops resuming it, writes the post-mortem, tags and deletes the branch, and tables the idea for a future revisit. --> How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stop a plan for good, and make every piece of tooling agree that it stopped.
The argument is: $ARGUMENTS
An abort that lives only in a chat window is not an abort. A plan killed at 4 of 9 substeps is
byte-identical to one that merely stalled — same unchecked boxes, same Ledger, same branch — so
/continue's plan probe finds it, reconciles it, and reports "next: substep 2.3" to a session
weeks later. This command exists to leave a terminal state on disk.
Step 0: Identify the plan, and confirm
Resolve $ARGUMENTS to one plan doc — scan both docs/*.md and .claude/plans/*.md (a plan
lives in either; the second is gitignored in some repos). Match on the alias in the filename or
the H1. If the argument is empty, infer from what this session has been executing.
Then read three slices — the header, the substep checkboxes, and the Ledger tail — and report before changing anything:
- how far it got (
N of M substeps checked), - its branch and worktree, and whether any of the branch is already in
main, - the reason being recorded.
⛔ Ambiguous or zero matches → stop and ask. Never guess which plan to kill. And if
/fleet shows a live sibling session on this plan's branch, stop: aborting under a session
that is mid-substep destroys uncommitted work. Report the sibling and stand down.
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.
- 9d ago First seen · 121 lines · 0 tokens per session scan C f027dece50db
abort-plan is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,575 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.