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 KKenny0/Tracework --skill capturegit clone --depth 1 https://github.com/KKenny0/TraceworkWrote 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/kkenny0/tracework/capture)<a href="https://agentmods.dev/skills/kkenny0/tracework/capture"><img src="https://agentmods.dev/badge/skills/kkenny0/tracework/capture/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/kkenny0/tracework/capture"><img src="https://agentmods.dev/badge/skills/kkenny0/tracework/capture.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 | $0.00207 | $0.02122 |
| Opus 5.5 | $0.00083 | $0.00849 |
| Sonnet 5.5 | $0.00041 | $0.00424 |
| Haiku 4.5 | $0.00021 | $0.00212 |
Grade A, and why
capture 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 280 B
- references/capture-corrections.md 2.5 KB
- references/capture-day.md 6.3 KB
- references/capture-entry-writing.md 16 KB
- references/capture-operations.md 8.8 KB
- references/capture-routing.md 3.4 KB
- references/tracework-storage-convention.md 40 KB
- scripts/tracework_raw.py 56 KB runs code
- scripts/tracework_sessions.py 23 KB runs code
- scripts/tracework_state.py 12 KB runs code
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.
- 9d ago Changed · +3 lines 4313f33b35cf
- 26d ago Changed · -1 lines bbec4c04b892
- 1mo ago Changed · +4 lines · +23 tokens per session 935f78aab754
- 1mo ago First seen · 186 lines · 184 tokens per session scan A 4d3d948e301a
capture is a skill published in the GitHub repository KKenny0/Tracework (2 stars, last pushed 4d ago), with no licence file. It adds 207 tokens to every session and 2,122 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
lane-memory
A file-based store for durable project facts that cannot be reliably inferred from source code or its module map.
winnow
How to read winnow stubs in tool results. A block marked "[winnow] ... hidden" was judged unlikely to matter for the current task and replaced with a short summary plus a recall key; call winnowrecall to restore it. Use when a tool result contains "[winnow]" lines or when winnowrecall / winnowstats tools are available.
catchup
Restore context after /clear by summarizing recent work and project state.
agent-log
Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger when the user explicitly asks to use agent-log or record/update an agent log entry; when planning, implementing, or finalizing a significant feature in a repo with an existing .agents/log; or before…
vibe-coding-survival
A practical guide for managing projects built with AI that writes code, often called vibe coding. It covers keeping decisions recorded, limiting the work in progress, saving usable versions, and checking that changes really work.
learning
Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.