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/kensaurus/cursor-kenji/complete-everythinggit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWhat 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 | $0.00020 | $0.00457 |
| Opus 5 | $0.00010 | $0.00229 |
| Sonnet 5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
complete-everything 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 yesterday.
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.
What it actually says
Complete Everything
Follow the complete-everything skill end to end. This command is a thin
entry point; do not replace the skill with a shorter improvised workflow.
In brief:
- Recover the full plan, prior completion report, diffs, and every connected item parked as out of scope, follow-up, optional, nice-to-have, or future work.
- Write the closure set and observable acceptance criteria to
.cursor/complete-everything-state.md. - Use host continuation as well as instructions: the packaged Cursor stop hook
follows unfinished state files; on Claude Code 2.1.139+ the strongest entry
is
/goal All actionable items in .cursor/complete-everything-state.md are checked, fresh applicable verification passes after the final edit, and completion-judge returns PASS. - Implement every item without pausing between milestones. Research uncertain approaches, append connected discoveries, and repair validation failures immediately.
- Compose the applicable skills:
burndown-full,test-unit,audit-fe-api,debug-fe-be-integration,audit-performance, andtest-playwright. - Run fresh diagnostics, typecheck, lint, tests, API/backend checks, build, and real user-flow smoke as applicable. A failure loops back to implementation.
- Invoke
completion-judgewith the plan, state file, full diff, baseline, and fresh evidence.CONTINUEloops back;BLOCKEDis not success. - Report only evidence. A real human decision or protected operation is blocked, never mislabeled as complete or deferred.
The full playbook lives in the complete-everything skill.
Related: burndown-full for mechanical coverage, verification-before-completion
for evidence levels, workflow-quality-gate for release assessment, and
full-stack-ship-discipline for backend deployment.
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.
- yesterday First seen · 40 lines · 20 tokens per session scan A a9fba4d26bf4
complete-everything is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 457 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
commit-msg
Cursor tooling: skills, rules, subagents.
code-review
Confidence-based code review checklist.
prp-new
Create new Product Requirement Prompt from scratch.
boot
Initialize agent, verify setup, and load rules.
clean
Repository hygiene — clean temp files, organize execution folders.
context
Dynamic context management — status, clean, log, save, read.