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 skills add KashZod/devloop --skill implementgit clone --depth 1 https://github.com/KashZod/devloopWrote 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/skills/kashzod/devloop/implement)<a href="https://agentmods.dev/skills/kashzod/devloop/implement"><img src="https://agentmods.dev/badge/skills/kashzod/devloop/implement.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 5.1 | $0.00068 | $0.05717 |
| Opus 5 | $0.00034 | $0.02858 |
| Sonnet 5 | $0.00014 | $0.01143 |
| Haiku 4.5 | $0.00007 | $0.00572 |
Grade A, and why
implement 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 6d 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Process (Test-Driven)
Implement the plan for: $ARGUMENTS
Tests give the implementer a self-verification loop. Instead of producing code that looks right, write tests first, then implement until they pass, so correctness is checked by execution rather than by inspection.
This skill is the build half of the loop. The plan half, code
exploration, chunk decomposition, and the plan-review gate, lives in the
companion /plan skill, which produces the tracker this skill reads. A
skill cannot invoke another skill, so if no approved tracker exists yet,
this skill stops and asks you to run /plan first.
Mapping to the Explore -> Plan -> Code Loop
| Workflow Phase | Implement Phase | What Happens |
|---|---|---|
| Explore / Plan | (done in /plan) |
Analysis, chunking, and plan review already happened |
| Explore | Phase 1: Load the Plan | Read the tracker, verify the gate, orient on the next chunk |
| Code | Phase 2: TDD Cycle | Per chunk: failing test -> code -> passing test |
| Verify | Phase 3: Quality Verification | review-impl + red-team gate; converge |
| Commit | (user-initiated) | Commit when the user requests |
When to Use This Process
| Scope | Approach |
|---|---|
| Trivial (typo, rename, version bump) | Don't use this skill -- just do it directly |
| Anything larger | Run /plan first to produce a tracker, then /implement builds it |
/plan sizes the work (a small fix becomes a 1-chunk tracker; a
cross-cutting feature becomes a layered one). This skill reads whatever
the tracker holds and builds it chunk by chunk. If you invoke
/implement with no tracker in place, it will point you at /plan.
Supporting Files
Load these on demand, not all upfront:
| File | When to Load |
|---|---|
| tracker-schema.md | Phase 1, to read/update tracker status and resume fields |
| quality-checklist.md | Phase 3 (final verification, or agent-failure fallback) |
What ships with it
1 file 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.
- 6d ago First seen · 507 lines · 68 tokens per session scan A 16419f8bb558
implement is a skill published in the GitHub repository KashZod/devloop (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 68 tokens to every session and 5,717 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
tdd
Test-driven development with red-green-refactor loops around vertical slices (tracer bullets), not horizontal layers. Use when asked to "use TDD", "write test-first", "red-green-refactor", "build this with tests", or when a feature has a clear observable contract. The discipline complement to the test/add-tests skills…
superpowers
Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.
openspec-plus-tdd
MANDATORY skill that activates whenever code is written to implement an OpenSpec change task. Triggers: openspec-plus-apply is active, /opsx-apply is running, the user is implementing tasks from an OpenSpec change, an implementer subagent dispatched by openspec-plus-apply is starting work, or the user invokes phrases…
plan-pipeline-execute
Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.
speq-implement
Orchestrate implementation of a reviewed plan: task breakdown, TDD sub-agents, code review, and verification report. Use when the user asks to implement, build, or execute a plan under specs/plans/ — after /speq-plan, before /speq-record. Arg: .
speq-code-guardrails
TDD cycle and code quality guardrails — failing-test-first, evidence, dependency, error-handling, and test-quality rules. Triggered by implementer-agent, implementer-expert-agent, and code-reviewer before any implementation or review work.