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/rajconnects/founder-stack/mission-abortgit clone --depth 1 https://github.com/rajconnects/founder-stackWrote 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/rajconnects/founder-stack/mission-abort)<a href="https://agentmods.dev/commands/rajconnects/founder-stack/mission-abort"><img src="https://agentmods.dev/badge/commands/rajconnects/founder-stack/mission-abort.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 | $0.00029 | $0.00902 |
| Opus 5 | $0.00015 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
mission-abort 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are aborting an in-flight mission.
Arguments: $ARGUMENTS
Steps
-
If
$ARGUMENTSis empty: printERROR: /mission-abort requires a mission id. Run /mission-status to see active missions.and stop. -
Parse: first whitespace-separated token is the id; remainder is the abort reason (may be empty).
-
Read
.claude/project.json→mission_root. Confirm<mission_root>/<id>/state.jsonexists. -
Read the state. If
statusis alreadycompletedoraborted: printMission <id> already <status>. Nothing to do.and stop. -
Confirm with the user. Print:
About to abort mission <id> (goal: <goal>). Status: <status> Features: <completed>/<total> completed Reason: <reason or "not provided"> This will: - Set status: aborted in state.json - Append a final log entry - Stop further /loop wakeups - Preserve the mission directory at <mission_root>/<id>/ for audit - NOT roll back any code changes the worker made — review with git diff Proceed? (yes/no)On
no: stop. -
Perform the abort synchronously (small enough to inline):
- Set
state.jsonstatus: aborted. Appenderror_logentry with timestamp + the parsed reason (or"user-initiated abort"if empty). - Save state atomically.
- Append to
log.md:<timestamp> | mission aborted by user. - Remove the mission-mode marker for this mission:
rm -f "$CLAUDE_PROJECT_DIR/.claude/.mission-tick-active-<id>". Otherwisemain-push-guard.shwould keep blocking interactive pushes to main after the mission is gone. - Close the coordination.json row if it exists: set
status: completed,completed: <iso>. Do not usecompleted_unclean— that status is reserved for crashed sessions and could trigger a future automated sweep to remove the worktree, which would defeat the audit-trail guarantee. The mission-level "aborted" signal lives instate.json.status, not in the coordination row. - Do not delete files (other than the mission-mode marker). Do not call memory-broker. The mission directory and the worktree are preserved for audit.
- Set
-
Worktree cleanup hint. If
state.worktreeis set, print:Worktree preserved at <state.worktree.path> on branch <state.worktree.branch>. To inspect: cd <state.worktree.path> && git status To discard: git worktree remove --force <state.worktree.path> && git branch -D <state.worktree.branch> -
Cron pace cleanup. If
state.pace == "cron": invoke the/scheduleskill via the Skill tool to delete the routine namedmission-<id>. If deletion fails (already gone), log a warning but don't fail — the user invoked abort with clear intent. If state.pace is local, skip (nothing to clean up). -
Suggest:
Review code changes with: cd <state.worktree.path> && git diff <state.worktree.base_ref> (or `git diff` from the main repo if worktree is disabled) Review mission with: cat <mission_root>/<id>/log.md
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 · 67 lines · 29 tokens per session scan A 97f89da2cfd5
mission-abort is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 902 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
project-recap
Generate a visual project recap for context switching.
os-meeting
快速创建和管理AI团队会议.
workspace
Testany Workspace, 管理工作空间,成员权限,团队组织.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).