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/kashzod/devloop/plannpx skills add KashZod/devloop --skill plangit clone --depth 1 https://github.com/KashZod/devloopWhat 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 | $0.00069 | $0.03541 |
| Opus 5 | $0.00034 | $0.01770 |
| Sonnet 5 | $0.00014 | $0.00708 |
| Haiku 4.5 | $0.00007 | $0.00354 |
Grade A, and why
plan 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.
How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Process (Chunk Decomposition + Plan Review)
Plan the following before implementation begins: $ARGUMENTS
Planning decides HOW to build what the spec described. Fixing a wrong
abstraction in a plan costs minutes; fixing it in code costs hours. So
this skill produces a reviewable plan, a JSON tracker of independently
testable chunks, and runs it through an independent plan-review gate
before any code is written. When the gate passes, hand off to
/implement.
Mapping to the Explore -> Plan -> Code Loop
| Workflow Phase | Plan Phase | What Happens |
|---|---|---|
| Explore | Phase 1: Analysis | Read files, trace data flow, check standards |
| Plan | Phase 2: Decompose | Chunk breakdown, dependency graph |
| Plan | Phase 3: Tracker | Write the JSON tracker (source of truth) |
| Plan | Phase 4: Present | Present the plan, get explicit approval |
| Plan | Phase 5: Review Gate | review-plan agent gates the plan |
Code and Commit happen in the companion /implement skill, which reads
the tracker this skill produces.
When to Use This Process
| Scope | Approach |
|---|---|
| Trivial (typo, rename, version bump) | Don't plan -- just do it directly |
| Small (single-file logic, simple bug fix) | Small feature shortcut (1-chunk tracker) |
| Medium+ (multi-file, unfamiliar code) | Full process |
| Large (cross-cutting, multi-session) | Full process, thorough decomposition |
Small feature shortcut: For single-file or few-file changes with no new domain logic, collapse Phase 2 to a single chunk and keep Phase 4 (present) light, but still write the tracker (Phase 3) and run the Phase 5 review gate. Small features carry the same regression risk, so the gate is not optional. Use a 1-chunk tracker (see tracker-schema.md §Single-Chunk Features).
Supporting Files
Load these on demand, not all upfront:
| File | When to Load |
|---|---|
| chunk-template.md | Phase 2, when decomposing into chunks (skip for small features) |
| tracker-schema.md | Phase 3, when creating the tracker (all features) |
| quality-checklist.md | Phase 5, only as the fallback self-check if the review-plan agent is unavailable |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 366 lines · 69 tokens per session scan A 26e51a528ffd
plan is a skill published in the GitHub repository KashZod/devloop (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,541 once invoked, about $0.0003 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
align
Interview the person before implementation when requirements, scope, expected behavior, design, or an important assumption needs shared agreement.
diff
Use when someone asks to explain or review a GitHub pull request as an evidence-linked, self-contained offline HTML review.
spring-boot-4-conventions
Spring Framework 7 / Spring Boot 4 idioms and defaults. Use when writing or reviewing controllers, services, configuration, HTTP clients, async/virtual-thread code, or anything touching Spring's programming model.
performance-optimization
Spring Boot 4 / JVM performance work — measure first, then fix. Profiling (async-profiler, JFR, JMH), Micrometer, common Spring antipatterns (N+1, unbounded lists, HikariCP sizing, virtual-thread pinning), caching, GC, and SLO-driven work. Used by /plan for risk callouts and by /review to flag perf regressions.
maven-harness-pom
Reference Maven POM fragments for the full harness — Spotless, Checkstyle, SpotBugs, Error Prone, JaCoCo, PIT, OpenAPI generator + diff, OWASP dependency check, Surefire/Failsafe. Use when wiring the harness into a new project or upgrading a brownfield POM.
shipping-and-launch
Pre-deploy hygiene for a Spring Boot 4 feature — verify gates, capture rollback plan, sign off observability, generate release notes, and stage the rollout. Used by /ship after /review approves the diff. The agent never deploys; it produces the plan a human executes.