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 minusblindfold/devloop --skill implementgit clone --depth 1 https://github.com/minusblindfold/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/minusblindfold/devloop/implement)<a href="https://agentmods.dev/skills/minusblindfold/devloop/implement"><img src="https://agentmods.dev/badge/skills/minusblindfold/devloop/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/minusblindfold/devloop/implement"><img src="https://agentmods.dev/badge/skills/minusblindfold/devloop/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 | $0.00038 | $0.01719 |
| Opus 5.5 | $0.00015 | $0.00688 |
| Sonnet 5.5 | $0.00008 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
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 2mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute each section in order. Copy the checklist and check off items as you complete them. Do not proceed past a Gate until verified.
Artifact: The worker writes an implementation note to .work/implementations/ — even if the task is incomplete.
Constraint: You are the foreman — you do not implement tasks yourself. A fresh-context worker subagent implements the selected task; you build its payload, verify its return, and own the plan checkboxes.
Find the feature
Check .work/active/ for marker files. If exactly one exists and no $ARGUMENTS provided, auto-select that feature's slug. If multiple markers exist, list them, offer to archive any with date older than 30 days to .work/archive/, then ask. Arguments always override.
Parse $ARGUMENTS as <slug>, <slug> <task-N>, or <slug> all. If the marker has stage: mini-spec, read the brainstorm artifact's ## Mini-Spec section as the spec — a single task (N = 1), no plan or design required; skip task picking. Otherwise find the plan in .work/plans/ and matching design in .work/designs/. Missing design → print "No design found. Run /dl:design first." and stop. No argument → list plan/design pairs; none: stop; one: confirm; many: ask to pick.
Task Progress:
- [ ] Find plan and design by slug
- [ ] Read plan and design; read completion state from the plan's checkboxes
- [ ] Pick task from args or ask — `all`: require clean tree, then loop per All mode
- [ ] Build the worker payload (task entry, design spec, rules, prior notes)
- [ ] Spawn the worker; receive its structured return
- [ ] Verify: note exists, STATUS complete, tests pass
- [ ] Check off the task in the plan (all mode: commit, then next task or halt)
- [ ] Gate: verify note with ls; update active marker
- [ ] Wrap up: summarize worker return(s), note deviations, suggest commit (all mode: end with forked review's findings)
Load
Read plan and design in full. The plan's - [ ] checkboxes are the authoritative completion state — task numbers are positional. Print the task list with status.
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.
- 2mo ago First seen · 89 lines · 38 tokens per session scan A 273aca3ebca8
implement is a skill published in the GitHub repository minusblindfold/devloop (1 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,719 once invoked, about $0.0002 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
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
coordinator
Runs the research-team plugin's multi-agent research pipeline end-to-end from the main thread: decomposes a topic into 2-5 subtopics, spawns parallel research-team:research-specialist subagents for each, verifies their output on disk, then spawns a research-team:research-report-writer subagent to synthesize the final…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
report-formats
Output formats and report templates for the research-team plugin's reports. The research-report-writer agent loads this skill for every report. It also applies when a user asks for a research report, technical survey, decision brief, landscape scan, what's-new digest or source summary in a particular editor's format…
slideware
Create visually rich, style-driven slide decks in two output formats: PowerPoint (.pptx via pptxgenjs + React icons) and HTML (single-file Reveal.js deck). Use any time the user asks for a slide deck, presentation, pitch deck, training module, keynote, .pptx file, HTML/web presentation, Reveal.js deck, browser slides…