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 bdfinst/agentic-dev-team/plugin install dev-teamWrote 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/bdfinst/agentic-dev-team/apply-test-doubles)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/apply-test-doubles"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/apply-test-doubles/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/bdfinst/agentic-dev-team/apply-test-doubles"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/apply-test-doubles.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 | $0.00131 | $0.04452 |
| Opus 5.5 | $0.00052 | $0.01781 |
| Sonnet 5.5 | $0.00026 | $0.00890 |
| Haiku 4.5 | $0.00013 | $0.00445 |
Grade A, and why
apply-test-doubles 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 1mo 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Test Doubles
Role: worker. Applies ../cd-test-architecture/SKILL.md's Step 4b
build-vs-document decision logic against a resolved report — one already
saved on disk, or a fresh one produced by assessing a target — without
re-running the full Steps 0-6 assessment when a valid report already
exists.
You have been invoked with the /apply-test-doubles command.
Parse Arguments
Arguments: an optional positional <report-path-or-target>, an optional
--component <name>, and an optional --yes.
<report-path-or-target>— a path to a previously saved/cd-test-architecturereport, or a target application/repo path to assess when no such report exists yet. May be omitted entirely — see the absent-path row below.--yes— run non-interactively: this step's own re-entrant Step 4b prompt (Step 2) is skipped, perhuman-oversight-protocol's--yes/DEV_TEAM_AUTO_APPROVE=1/ no-TTY convention — see Step 2 for the exact per-component behavior.--component <name>— scope processing to one named component. Applied as a post-hoc filter over the resolved report's already-existing rows, identically on both paths — never forwarded ascd-test-architecture's own--componentargument on the target path. A single-component-scoped target-path assessment can legitimately produce no report file at all (cd-test-architecture's Output is.dev-team-reports/cd-test-architecture-<app>.md, "or chat for a single component"), which would leave this skill's own fast path with nothing to read — so the target-path self-invocation always assesses the full target, and--componentnarrows the result afterward, identically to the fast path.
Steps
1. Resolve report or target
Every invocation resolves to exactly one report before anything else in this skill runs — either an existing one read directly (the fast path), or a fresh one produced by assessing a target (the target path). This is one branch point, not two independently-described procedures: whichever state below applies, resolution ends at the same "read the report" step.
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.
- 1mo ago First seen · 322 lines · 131 tokens per session scan A 552fa344288d
apply-test-doubles is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 131 tokens to every session and 4,452 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.