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/prunegit 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 | $0.00031 | $0.00262 |
| Opus 5 | $0.00015 | $0.00131 |
| Sonnet 5 | $0.00006 | $0.00052 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
prune scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Below is the engine's dry run: what would be deleted. This call never deletes anything, and command arguments are deliberately not forwarded into it.
The user does NOT see this raw output — retell the list yourself (id, status, title) and ask whether to delete. Do not write "see above".
Delete only after the user's explicit go-ahead, with exactly this command:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/backlog.py" prune --yes
That call is not pre-authorised — the permission rule above covers the dry run only, so deletion always goes through a permission prompt. That is deliberate: it keeps the user's approval a property of the harness rather than of these instructions. Retell its output (what was deleted, what failed) yourself.
If the engine said "Nothing to prune" — pass that through and ask nothing.
!python3 "${CLAUDE_PLUGIN_ROOT}/scripts/backlog.py" prune 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.
- yesterday First seen · 26 lines · 31 tokens per session scan A 0479512d61c7
prune is a command published in the GitHub repository SI-IC/backlog-skill (1 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 262 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
sync
Sync the audit manifest with Azure DevOps work items — set the connector up for the first time (connect: verify the transport, report which auth path is in effect, prove access read-only, detect the board's process), push manifest bugs/tasks/phases to ADO (board states, sprint stamp, Remaining Work, comments), pull…
factory
Run one pass of the ticket queue — scan the tracker for human-authorized tickets, claim one, and route it to the right workflow (spec a raw ticket, groom the backlog, hunt a bug, or build an approved spec in its own worktree via /sonu:build). You are the trigger; there is no daemon. Never merges and never authorizes…
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
task-hunter.skeleton
Kullanicinin girdisini asagidaki kurallara gore cozumle.
task-conductor.skeleton
/task-conductor top 5 -> /task-conductor plan top 5 /task-conductor all -> /task-conductor plan all /task-conductor 3,5,8 -> /task-conductor plan 3,5,8 /task-conductor keyword auth -> /task-conductor plan keyword auth.
deadcode.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects Ornek cikti.