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 plangit 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/plan)<a href="https://agentmods.dev/skills/minusblindfold/devloop/plan"><img src="https://agentmods.dev/badge/skills/minusblindfold/devloop/plan/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/plan"><img src="https://agentmods.dev/badge/skills/minusblindfold/devloop/plan.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 | $0.00033 | $0.00850 |
| Opus 5.5 | $0.00013 | $0.00340 |
| Sonnet 5.5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
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 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 — 75 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: Write to .work/plans/. Verify with ls before wrapping up.
Constraint: Do not write code. This skill produces a plan, not an implementation.
Mode
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.
If $ARGUMENTS (or auto-selected slug) matches a file in .work/plans/ → refine mode. If ambiguous, list and ask. Set but no match → create mode. Empty → list .work/plans/; none: ask what to plan; one: offer refine or new; many: numbered list, ask to pick.
Task Progress:
- [ ] Determine mode
- [ ] If refine: read current plan, check for new brainstorm/research artifacts
- [ ] Gather context: project rules, CLAUDE.md, project scan, brainstorm/research artifacts
- [ ] List context and ask clarifying questions (only unresolved items)
- [ ] Decompose the work into plan tasks (checkbox list)
- [ ] Write plan to .work/plans/
- [ ] Gate: verify plan with ls; update active marker
- [ ] Present plan for spot-check
Context gathering
Read devloop/rules/*.md if present — apply rules whose keywords match the feature; rules without keywords always apply. Read CLAUDE.md if present. Scan project directory structure. Check .work/brainstorms/ and .work/research/ for matching artifacts — read them if found. If research contains linked repo context, note it.
Clarifying questions
List what you found before asking. Ask 3-5 clarifying questions. Read decisions from brainstorm and recommendations from research — only ask about genuinely unresolved items. Wait for answers.
Task creation
Write each task as a - [ ] checkbox in the plan — the checkboxes are the authoritative completion state that /dl:implement tracks. Decompose by user-visible behavior or capability, not by architectural layer. Do not create tasks like "set up all database models," "build the service layer," or "add tests for everything" — each task should touch all relevant layers for its slice. Order by dependency, then by what unblocks the most follow-up work.
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 · 75 lines · 33 tokens per session scan A 51b28bf2ec44
plan is a skill published in the GitHub repository minusblindfold/devloop (1 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 850 once invoked, about $0.0001 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
matilha-hunt
Use when user is ready to dispatch a wave's subprojects — creates git worktrees and kickoff.md per SP, writes wave-NN-status.md, prints dispatch commands.
matilha-init
Use when starting a new project or initializing Matilha in an existing one — scaffolds project-status.md, AGENTS.md, CLAUDE.md/GEMINI.md, and phase 0 artifacts.
matilha-howl
Use when user asks about project state, current phase, active waves, or next action — reads project-status.md and surfaces the status in a stream-friendly format.
tasks
Manage tasks and plans using the .tasks/ directory.
techpack-settings
Component type definitions, settings schemas, directory patterns, and validation rules for the fullstack-typescript tech pack.
config-orchestration
Orchestrates project configuration operations — generate, validate, diff, and add-env.