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/kingemma7/cursor-os/implementation-loopnpx skills add KingEmma7/cursor-os --skill implementation-loopgit clone --depth 1 https://github.com/KingEmma7/cursor-osWhat 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 | $0.00033 | $0.00381 |
| Opus 5 | $0.00016 | $0.00191 |
| Sonnet 5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
implementation-loop 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
Implementation Loop
A repeatable loop for shipping a change that actually works and fits the codebase. Follow the phases in order; don't skip to coding.
1. Understand
- Restate the goal as explicit acceptance criteria. If the request is vague, ask or state your assumption.
- Read the relevant code,
AGENTS.md, anddocs/(architecture, repo-memory, decision-log) before designing. Match existing patterns. - Surface conflicts with the current codebase now, not after building.
2. Plan
- For multi-file or risky work, write a short plan: files to touch, the approach, and the verification you'll run.
- Choose the smallest complete solution. Reuse existing utilities and patterns before adding abstractions or dependencies.
3. Build
- Make surgical changes scoped to the goal. Don't refactor unrelated code in the same pass.
- Keep each modified file traceable to the request. Note unrelated issues separately instead of fixing them inline.
4. Verify
- Run the project's checks: types, lint, tests, and a manual check of the actual behavior. Don't assume — run them.
- Compare the result against
docs/quality-rubric.md. Cover edge cases, error states, and the failure modes the change introduces. - If checks cannot be run, explain exactly why and provide the safest manual verification path.
5. Report
- State what changed and why, how you verified it (commands and results), and any remaining risks or follow-ups.
- Update project memory: record durable facts in
docs/repo-memory.mdand append notable decisions todocs/decision-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.
- yesterday First seen · 36 lines · 33 tokens per session scan A 9c80de9657eb
implementation-loop is a skill published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 20d ago), licensed MIT. It adds 33 tokens to every session and 381 once invoked, about $0.0002 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 skills, from other repositories
onboard-repository
Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
encode-invariant
Convert accepted repository rules into the smallest repository-native mechanical validation with positive and negative proof and precise enforcement-level reporting. Use for requests to enforce architecture, reliability, security, or quality boundaries; prevent a documented violation from recurring; add structural…
daily-brief
Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.