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/nirecom/agents/supervisor-reportnpx skills add nirecom/agents --skill supervisor-reportgit clone --depth 1 https://github.com/nirecom/agentsWhat 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 | $0.00025 | $0.00672 |
| Opus 5 | $0.00013 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
supervisor-report 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoked by Claude Code itself when a trigger in rules/supervisor-reporting.md fires — never by a human, which is why user-invocable is false.
Procedure
SR-1. Resolve $SID: read the Session-ID: field of the worktree's WORKTREE_NOTES.md. Only if that file or field is absent, fall back to $CLAUDE_SESSION_ID — Anthropic bug #27987 makes its propagation into Bash unreliable, so it is the fallback, not the source. If neither resolves, still report: state in your turn output what you observed and that no session id could be resolved.
SR-2. Choose categories (comma-separated, multi-select), severity, detail (what was observed, free text), and reporter (the skill or agent name) from the tables below.
SR-3. Run, as one Bash call: node "$AGENTS_CONFIG_DIR/bin/supervisor-report" --categories <cats> --severity <sev> --detail "<text>" --reporter "<name>" --session-id "$SID". All four flags are mandatory — the CLI aborts when one is missing.
<text> is observation text that may come from tool output or a file, so treat it as untrusted: before substituting it, strip every `, $, \, ", newline and control character from it, and collapse the remainder to a single line — a $(...) or backtick left in the detail executes inside the double-quoted argument.
Text you cannot safely reduce that way must not be interpolated at all: shorten the detail to your own one-line summary and leave the raw text out.
SR-4. Never swallow a non-zero exit. Put the fact that the report failed, plus the CLI's stderr, in your turn output: a lost observation is the worst failure mode of this skill.
Categories
| Category | When to use |
|---|---|
intent |
Scope or non-goal misalignment with intent.md |
outline |
Approach selection or delivery plan issue |
detail |
File-level implementation plan inconsistency |
workflow |
Workflow rule violation, step skip, sentinel issue |
code |
Code writing issue (logic error, naming, structure) |
test |
Test failure, flaky test, coverage gap |
security |
Credential leak risk, dangerous input handling |
performance |
Build/runtime slowdown, resource spike |
env |
Missing env var, dependency version mismatch |
other |
Does not fit any category above |
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 · 45 lines · 25 tokens per session scan A ca8db66734af
supervisor-report is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 672 once invoked, about $0.0001 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
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.