Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add choiyounggi/dev-loop/plugin install dev-loopWrote 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/choiyounggi/dev-loop/loop-implement)<a href="https://agentmods.dev/skills/choiyounggi/dev-loop/loop-implement"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/loop-implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/choiyounggi/dev-loop/loop-implement"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/loop-implement.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.05041 |
| Opus 5.5 | $0.00038 | $0.02016 |
| Sonnet 5.5 | $0.00019 | $0.01008 |
| Haiku 4.5 | $0.00009 | $0.00504 |
Grade A, and why
loop-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 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loop-implement — the single implementation loop, driven by a wiki-plan
Drive work to "done" through a closed, methodology-grounded loop (sources at the
bottom). This is dev-loop's one and only implementation skill — it both plans
(via wiki-plan, step 2) and executes, so there is no separate executor. The
plan wiki-plan produces is not a loose sketch: it fixes an ordered task list
and, for each task, navigates to the exact wiki pages that ground it (the
decision→page map). This loop consumes that plan directly — executing the
tasks in the plan's order, loading exactly the wiki pages each task names, and
citing them — so every change traces back to a verified wiki page.
It works the same whether it runs standalone (you produce the plan here in step 2) or as an orchestrated worker (the orchestrator hands you a task brief and the plan it already produced, and you adopt and implement it here). Either path, one loop.
When to use
- Use: logic changes, new features, bug fixes, behavior-changing refactors.
- Skip: typos, config values, simple rename/import cleanup, one-line edits.
Two entry modes (both run the SAME loop)
- A plan already exists (a
plans/<feature>/from a priorwiki-planrun, or handed to you by the orchestrator): skip producing one — execute its tasks in the## Task ordersequence, one at a time, each through steps 0 and 3–7 below, loading that task's named wiki pages. - No plan yet (a fresh standalone task): step 2 runs
wiki-planfirst to produce the ordered, wiki-navigated plan, then you execute it the same way.
The plan step is fixed (not pluggable)
Step 2 (Plan) is hardwired to the bundled wiki-plan skill and is
mandatory for every non-trivial task — it is not a pluggable role and cannot
resolve to inline planning. wiki-plan grounds each design decision in the
bundled wiki/ semantic layers before any code is written, so the implementing
pass executes decisions instead of guessing them. See step 2 below.
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.
- yesterday Changed · +2 lines 26dc1bdfc3d9
- 8d ago Changed · +1 lines 8185e6d97af1
- 10d ago Changed · +2 lines 2ae2513bee6a
- 29d ago Changed · +21 lines ca6584a1f867
- 1mo ago Changed · +5 lines d40d6f17c756
- 1mo ago Changed · +12 lines c91ce75331fe
- 1mo ago Changed · +21 lines 1c499fd22cdd
- 1mo ago First seen · 282 lines · 94 tokens per session scan A 5a0f4d10d07a
loop-implement is a skill published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 5,041 once invoked, about $0.0004 per session on Opus 5.5. 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
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.
ros2-development
Implement or change ROS 2 Jazzy packages, nodes, interfaces, launch files and configuration in a colcon workspace. Use for building and validating a development change, including tests that report success without running. For a live QoS, TF, IMU or odometry fault, use ros2-troubleshooting.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
test-quality-analysis
Analyze test code quality to detect coverage-only tests, test smells, and low-value assertions. Use when asked to "analyze test quality", "find coverage-only tests", "audit our tests", "are these tests valuable", "find test smells", or "which tests should we delete". Scores tests 1-5 on real value and produces…
agentic-eval
Patterns for agent self-improvement through iterative evaluation and refinement -- generate, evaluate, critique, refine loops that move beyond single-shot generation.
testing-strategies
Systematic testing for confidence without over-testing — the right test at the right level.