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 digital-stoic-org/agent-skills --skill reportgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/report)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/report"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/report/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/digital-stoic-org/agent-skills/report"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00918 |
| Opus 5 | $0.00034 | $0.00459 |
| Sonnet 5 | $0.00014 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report
One packet, one recipient: the orchestrator named in your mandate. It is the only message you ever send by machine — no peer roster exists and none can be acquired.
Read nothing. The skeleton below is complete. ../../references/protocol.md holds the reasoning, for whoever amends the contract; opening it here spends context on a file the orchestrator will never see.
1. Gate — report, or question?
"The scope I was given is wrong" is not a report. It is a QUESTION: addressed to the human, printed here in your own window, no machine path. Sent to the orchestrator it arrives buried inside a status packet — and in discovery it is the single most valuable thing you can surface. Stop and print it instead.
Everything else on your stop_conditions, and every cadence checkpoint → report.
2. Address
The orchestrator field of your mandate. Missing — never given, or dropped by a relay packet you inherited → stop, say so to the human in plain text, and print the report in your own window so its content survives. Never guess a name and never settle for a plausible one: likelihood lands a report in a stranger's window.
3. Fill
from: your own name
state: REPORT
stop_condition: which one of them fired
deliverable: the path from your mandate — written and up to date before you send this
established: each fact with the command that proves it
in_progress: what is half-done, and where it stands
next: what you would do if sent back in — a proposal, not a decision
what_i_do_not_know: ...
from— your own name, in the packet rather than left to the transport. The packet outlives the tube: quoted into a plan or carried into a relay, an unattributed report belongs to nobody.stop_condition— which one fired, quoted from the mandate.deliverable— write the file first, then send this. Your findings belong on disk, at the path your mandate gave you; the report points at them. A report that carries the content instead lands whole in the orchestrator's window and dies with yours. If your mandate named nodeliverable, say so here in those words rather than compensating with a longer report.established— every fact paired with the command that proves it, and each on one line. Write the command you actually ran; do not re-run it, and never reconstruct a plausible-looking one. The orchestrator acts on these and cannot tell a fact from a claim. This is the change in knowledge state, not the file: the detail is in thedeliverable.in_progress— what is half-done and where it stands.next— a proposal, not a decision. The redirect is the orchestrator's to write; anticipating it here does not make it yours.what_i_do_not_know— mandatory, never empty. A hidden gap reads as completeness, and the redirect gets built on it.
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.
- 4d ago Changed · +2 lines 7b54d07cbf74
- 8d ago First seen · 51 lines · 68 tokens per session scan A bf2a90ba6eae
report is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 918 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…