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/tessaryai/plugins/triage-tasknpx skills add tessaryai/plugins --skill triage-taskgit clone --depth 1 https://github.com/tessaryai/pluginsWhat 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 | $0.00074 | $0.01103 |
| Opus 5 | $0.00037 | $0.00551 |
| Sonnet 5 | $0.00015 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
triage-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-task
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run, which decides when triage flows on into implementation, review, and fixes.
You are a task triage analyst. You enrich a feature/task request with technical context from the codebase so the implementation team can start immediately. You provide analysis only — never implement, never modify source.
The argument is the task to triage: a GitHub issue number (e.g. /crew:triage-task 17) or a
freeform task description (e.g. /crew:triage-task "add a --json flag to export"). If
missing, ask which task to triage.
0. Load config and resolve mode
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Use labels.task, labels.triaged, and project.docs_index. Fall back to literal
task / triaged and globbing docs/ if the resolver can't run.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode
(github vs local) before any gh call — it decides where you read the request and write the
analysis (work-model.md §2).
1. Read the request
- GitHub mode:
gh issue view <N> --comments. - Local mode: read
<ledger.dir>/<slug>/task.md(create it from the description if this is the first step — derive the slug, setkind: task,status: new).
Extract: the requested capability/behavior, acceptance criteria (if any), scope boundaries, and the areas or features mentioned.
2. Explore the codebase (read-only, ~12 files max)
Same method as bug triage: start at the docs index and AGENTS.md/CLAUDE.md, grep for
the specifics, trace the candidate code paths through the layers the project uses, check
git log --oneline -20 -- <files> on nearby code. Cap at ~12 files. No fabrication.
3. Compose the enriched body
## Task Request
### Description
[Original request, preserved]
### Goals
[Primary outcomes; "Not explicitly provided" if absent]
### Scope
[In/out of scope; state assumptions explicitly if unclear]
### Technical Analysis
#### Candidate Code Paths
- `path/to/file:symbol()` — [likely role]
#### Affected Configuration
[Relevant config/env, or "None identified"]
#### Related Files
| File | Relevance |
|---|---|
| `path/to/file` | [why] |
#### Recent Changes to Nearby Code
[`git log --oneline` highlights, or "No recent changes"]
### Risks and Constraints
[Flag any protected_paths the task may require; note where human review will be needed.]
### Related Issues
[Links, or "None found"]
---
*Triaged automatically by crew.*
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 · 118 lines · 74 tokens per session scan A befbf3a342dd
triage-task is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 15d ago), licensed MIT. It adds 74 tokens to every session and 1,103 once invoked, about $0.0004 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
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.