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 lttr/claude-marketplace --skill ticket-commentsgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/ticket-comments)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/ticket-comments"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/ticket-comments/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/lttr/claude-marketplace/ticket-comments"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/ticket-comments.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 | $0.00043 | $0.01864 |
| Opus 5 | $0.00022 | $0.00932 |
| Sonnet 5 | $0.00009 | $0.00373 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
ticket-comments 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment on an AzDO Work Item (Markdown-aware)
There are two ways to put text on a work item's discussion. Use the Comments API, not the System.History patch.
| Method | Editable? | Deletable? | Markdown? |
|---|---|---|---|
PATCH workitems/{id} with System.History |
no | no | no (HTML-coerced) |
Comments API workItems/{id}/comments |
yes | yes | yes, via format=markdown query param |
The format flag lives in the query string, not the body. Omit it and the text is stored as HTML, so Markdown shows up literally.
This is work-item discussion only. For pull-request thread comments, use dev-azdo:pr-comments.
Step 1: Resolve org and project (always first)
Shell variables do not survive between Bash calls, so resolve these once, read the printed
values, and paste the literals into every later command. Never carry $BASE across calls.
# cut -f2- + sed, not `tr -d ' '`. AzDO project names may contain spaces.
TRIM="s/^ *//; s/ *$//"
ORG_URL="${AZDO_ORG_URL:-$(az devops configure --list | grep '^organization' | cut -d= -f2- | sed "$TRIM")}"
PROJECT="${AZDO_PROJECT:-$(az devops configure --list | grep '^project' | cut -d= -f2- | sed "$TRIM")}"
: "${ORG_URL:?no organization, set AZDO_ORG_URL or run az devops configure --defaults}"
: "${PROJECT:?no project, set AZDO_PROJECT or run az devops configure --defaults}"
echo "BASE=$ORG_URL/$PROJECT/_apis/wit/workItems"
If this command aborts with either :? message, stop and ask the user for their AzDO
organization URL and project. They are team-specific. Never guess them, never fall back to
an org name seen elsewhere in the repo or conversation. How the user persists the values (env
var, az devops configure --defaults) is their call.
The two constants below are fixed and can be typed literally. They need no resolution step:
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.
- 10d ago First seen · 143 lines · 43 tokens per session scan A b0b1278fdb54
ticket-comments is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,864 once invoked, about $0.0002 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
issue-triage
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
project-execution
Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.