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/agentic-development/adev-plugin/recovernpx skills add agentic-development/adev-plugin --skill recovergit clone --depth 1 https://github.com/agentic-development/adev-pluginWhat 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 | $0.00095 | $0.06349 |
| Opus 5 | $0.00048 | $0.03174 |
| Sonnet 5 | $0.00019 | $0.01270 |
| Haiku 4.5 | $0.00010 | $0.00635 |
Grade A, and why
adev:recover 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 2d 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Recovery Workflow
When a subagent gets stuck during /adev:implement, this skill provides a structured diagnosis, corrective injection, and resume cycle. Instead of blindly retrying or escalating to the user with vague "it did not work" messages, this skill classifies the root cause, applies the targeted fix, and re-dispatches with enriched context.
Arguments
--task <N>: recover a specific stuck task (references task number from the active plan)--blocker <path>: recover from a specific blocker file in.context-index/hygiene/blockers/- No arguments: interactive mode (check for recent blockers or ask which task is stuck)
--no-infra: skip infrastructure preflight checks (user-only — the agent must never set this flag)
Prerequisites
The project must have .context-index/ initialized with constitution.md and manifest.yaml. An active implementation plan should exist (produced by /adev:plan). If no plan is found, ask the user for the plan path.
Process
Announce at start:
Starting agent recovery workflow.
Mode: [task N | blocker <path> | interactive]
Step 1: Detect
Identify the stall point. The goal is to understand exactly where and why progress stopped.
With --task <N>
- Find the active plan. Look for the most recent plan file in
.context-index/specs/features/or ask the user for the path. - Load task N from the plan. Extract the task title, description, file list, dependencies, and specialist routing.
- Check if a blocker file exists at
.context-index/hygiene/blockers/for this task. - Check if a subagent report exists (from the last
/adev:implementrun). Look for status BLOCKED or NEEDS_CONTEXT in the report.
With --blocker <path>
- Read the blocker file at the specified path.
- Extract the task reference, error description, and any file references from the blocker.
- Locate the corresponding plan and task entry.
Interactive (no arguments)
- Scan
.context-index/hygiene/blockers/for blocker files created in the last 7 days. Sort by date descending. - If blockers exist, present them:
Recent blockers found: 1. 2026-03-18-user-profile-api.md — BLOCKED: missing auth context 2. 2026-03-17-payment-webhook.md — NEEDS_CONTEXT: Stripe event schema Select a blocker to investigate, or describe which task is stuck. - If no blockers exist, ask the user: "Which task is stuck? Provide a task number from the plan or describe the problem."
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.
- 2d ago First seen · 520 lines · 95 tokens per session scan A 7836936701c4
adev:recover is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 6,349 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.