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 commands/si-ic/backlog-skill/listgit clone --depth 1 https://github.com/SI-IC/backlog-skillWhat 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 | $0.00038 | $0.00341 |
| Opus 5 | $0.00019 | $0.00170 |
| Sonnet 5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
list scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Below is the backlog engine's default view (open items, sorted by priority then age). Arguments are deliberately NOT forwarded into the line below: text placed there reaches the shell verbatim, before this prompt reaches you.
If the user asked for a different view, run the engine yourself with only the
flags you recognise — --all, --sort date, --priority <low|medium|high> —
and never paste the user's text into the command:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/backlog.py" list --all
This raw output is NOT shown to the user: it is injected into your context only. The only backlog the user will see is the one you print in this reply yourself.
Render it: print the engine's table verbatim in a code block (so the columns keep their alignment), then one line with the number of open items. Do not reformat, do not invent, do not drop rows. NEVER write "the backlog is shown above", "see above" or anything similar — there is nothing above.
If the engine returned "Backlog is empty …" — pass that through and draw no table.
The user's request: $ARGUMENTS
!python3 "${CLAUDE_PLUGIN_ROOT}/scripts/backlog.py" list 2>&1 || true
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 · 31 lines · 38 tokens per session scan A daac771629bd
list is a command published in the GitHub repository SI-IC/backlog-skill (1 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 341 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 commands, from other repositories
promote-discussions
Check GitHub Discussions for highly voted learnings and promote them to Issues.
log-time
Log work hours on an Atera ticket.
create-ticket
Create a new service ticket in Atera.
update-ticket
Update fields on an existing Atera ticket.
contact-upsert
Create or update a contact, optionally assign to groups.
resume_handoff
Resume work from handoff document with context analysis and validation.