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 tobihagemann/turbo --skill triage-backloggit clone --depth 1 https://github.com/tobihagemann/turboWrote 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/tobihagemann/turbo/triage-backlog)<a href="https://agentmods.dev/skills/tobihagemann/turbo/triage-backlog"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/triage-backlog/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/tobihagemann/turbo/triage-backlog"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/triage-backlog.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 | $0.00052 | $0.00894 |
| Opus 5.5 | $0.00021 | $0.00358 |
| Sonnet 5.5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
triage-backlog 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Backlog
Decide, entry by entry, which improvements in .turbo/backlog.md are worth keeping.
Step 1: Read the Backlog and Merge Duplicates
Resolve the repo root with git rev-parse --show-toplevel, except inside a linked worktree — where git rev-parse --git-dir differs from --git-common-dir — in which case use the parent of the common dir.
When that root holds the legacy .turbo/improvements.md, carry it into .turbo/backlog.md before reading, with the Write or Edit tool. When .turbo/backlog.md does not exist, write the legacy content there with its # Improvements header changed to # Backlog. Otherwise, append each legacy entry that .turbo/backlog.md does not already hold word for word. Once .turbo/backlog.md holds every legacy entry, delete the legacy file. When the write or the deletion is refused, tell the user what is left to do.
Read .turbo/backlog.md under that root. When it does not exist or holds no entries, present "No backlog entries to triage." Then use the TaskList tool and proceed to any remaining task.
Merge entries that cover the same improvement into one entry that keeps every detail either held, write the merged entries back, and output which ones were merged. Update each Paired with line in counterpart entries that names a title the merge retired.
Number the remaining entries in file order.
Step 2: Assess Each Entry
Work from each entry's own text. Read the code an entry names only when its text is too thin to say what the entry is for.
For each entry, settle the two parts its question in Step 3 carries, without outputting them yet:
- Story — one sentence naming who benefits and what they get, in plain language a reader who has not seen the code can follow. When nothing changes for the person using the software, tell it from the maintainer's side: what the entry simplifies.
- Recommendation — keep or drop, with a one-line reason.
Recommend keeping an entry that serves a goal the person using the software actually has, fixes a problem that was observed, or simplifies existing code. Recommend dropping one that is theoretical or was never observed, is decoration, would be resolved by another entry's fix, or adds machinery no requirement demands. For an entry carrying a Revisit line, apply these criteria to the fuller version it describes as though its condition held; the condition being unmet is no ground to drop it. When the entry's text settles neither, recommend neither and name what is unclear.
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.
- 3d ago First seen · 50 lines · 52 tokens per session scan A 8907c2b55180
triage-backlog is a skill published in the GitHub repository tobihagemann/turbo (420 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 894 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-09.
triage-backlog compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triage-backlogtobihagemann/turbo | Skill | 420 | today | MIT | A | 52 | Claude Code |
| offensive-c2-frameworksSnailSploit/Claude-Red | Skill | 11k | yesterday | MIT | A | 250 | Claude Code, Codex |
| offensive-crypto-attacksSnailSploit/Claude-Red | Skill | 11k | yesterday | MIT | A | 261 | Claude Code, Codex |
| offensive-parameter-pollutionSnailSploit/Claude-Red | Skill | 11k | yesterday | MIT | A | 0 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 11k | yesterday | MIT | A | 113 | Claude Code, Codex |
| fiscalisteromainsimon/paperasse | Skill | 2.6k | today | MIT | A | 306 | Claude Code |
| comptableromainsimon/paperasse | Skill | 2.6k | today | MIT | A | 248 | Claude Code |