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 bjorn-ingmanson/thefroject-plugins --skill outputs-triagegit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/outputs-triage)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/outputs-triage"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/outputs-triage/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/bjorn-ingmanson/thefroject-plugins/outputs-triage"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/outputs-triage.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 | $0.00050 | $0.01004 |
| Opus 5 | $0.00025 | $0.00502 |
| Sonnet 5 | $0.00010 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
outputs-triage 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outputs Triage
Move loose files into the right home and surface tasks buried in notes. Quick decisions, not deep analysis.
Execution Style
This skill makes routing decisions, not strategic ones. Be fast. Target under 10 seconds per item. If the right destination isn't obvious, leave the file alone and flag it for the user.
Gather Context First
- Read
context/for the active project structure and conventions - Identify the existing subdirectories under
outputs/(these are the routing targets) - Check
plans/for active plan names — files referencing them route there - Read the latest weekly plan for current priorities
The Triage Sequence
Pass 1 — Loose files in outputs/
Scan outputs/ for files at the top level (not inside a subdirectory).
For each loose file, decide:
| Pattern | Route to |
|---|---|
| Filename contains a project name | outputs/<project>/ |
| Filename contains a person's name | outputs/people/<name>/ if it exists, else flag |
| Filename starts with a date | Likely a meeting note — outputs/meetings/ |
| Marketing asset (image, post copy, ad) | outputs/marketing/ |
| Audit or report | outputs/audits/ |
| Transcript | outputs/transcripts/ |
| Cadence artifact (weekly/quarterly) | outputs/cadence/ |
| Stale draft (not modified in 30+ days, no clear home) | Flag for user to delete or keep |
If the right subdirectory does not exist, propose creating it — don't auto-create more than 2 new subdirectories per run (avoids fragmentation).
Pass 2 — Scattered tasks in notes
Find unchecked task items (- [ ]) across:
notes/(any subdirectory)outputs/(any subdirectory)plans/(active plans)
For each task:
| Task type | Route to |
|---|---|
| Tied to an active priority in this week's plan | outputs/cadence/weekly-plan-current.md (or note in the existing plan) |
| Tied to a quarterly priority | Surface in next weekly review for prioritization |
| Tied to a specific person (follow-up) | outputs/people/<name>/follow-ups.md |
| Tied to a project | The project's plan or its outputs/<project>/ directory |
| Stale (90+ days old, no progress) | Propose dropping |
| Unclear | Leave it, flag the file path for user |
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.
- 12d ago First seen · 115 lines · 50 tokens per session scan A 67a770425879
outputs-triage is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,004 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.