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/minusblindfold/devloop/researchnpx skills add minusblindfold/devloop --skill researchgit clone --depth 1 https://github.com/minusblindfold/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 | $0.00036 | $0.00899 |
| Opus 5 | $0.00018 | $0.00449 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
research 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 — 88 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/research/. Verify with ls before wrapping up.
Constraint: You MUST NOT modify project files. This skill produces context, not code.
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.
Parse $ARGUMENTS (or auto-selected slug): matches existing file in .work/research/ by slug → re-entry. Set but no match → create. Empty → stop and return, asking the caller for a topic.
You run in a forked context and cannot converse — when a choice is genuinely required (multiple current markers, no topic), stop and return the options to the caller instead of asking.
Find matching brainstorm artifact in .work/brainstorms/ and extract its ## Research Queries section. If missing, note it and derive queries from the given topic directly.
Task Progress:
- [ ] Determine mode; find and read brainstorm artifact (missing: derive queries from topic)
- [ ] If re-entry: read existing research artifact
- [ ] Read project rules from devloop/rules/
- [ ] Execute each research query as targeted search
- [ ] List findings per query in response
- [ ] Synthesize: identify gaps across queries
- [ ] Write artifact (create: new file; re-entry: append dated section)
- [ ] Gate: verify artifact with ls; update active marker
- [ ] Wrap up: summarize, suggest /dl:plan
Query execution
Read devloop/rules/*.md if present — apply rules whose keywords match the topic; rules without keywords always apply. If a matched rule declares repos:, include those repos in the search. For each query from the brainstorm artifact, search the codebase with targeted reads and greps. Record findings per query — keep findings factual, not opinionated. When a query touches an existing feature, note how it's structured through the stack (e.g., route → service → model → test) — this gives plan concrete examples for vertical slicing.
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 · 88 lines · 36 tokens per session scan A e82dd4347507
research is a skill published in the GitHub repository minusblindfold/devloop (1 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 899 once invoked, about $0.0002 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
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
bug-report
Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.
security-audit
Java security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java. Use when reviewing code security, before releases, or when user asks about vulnerabilities.
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
issue-triage
Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…