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 skills/meherbhaskar/temporal-debug-skill/temporal-debugnpx skills add MeherBhaskar/temporal-debug-skill --skill temporal-debuggit clone --depth 1 https://github.com/MeherBhaskar/temporal-debug-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 | $0.00077 | $0.02071 |
| Opus 5 | $0.00039 | $0.01035 |
| Sonnet 5 | $0.00015 | $0.00414 |
| Haiku 4.5 | $0.00008 | $0.00207 |
Grade A, and why
temporal-debug 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Temporal Debug Skill
Goal
Help the user debug a bug by reconstructing the code state at the time the bug
occurred, rather than analyzing the current HEAD. This eliminates confusion
from recent unrelated changes.
When to Use
- User mentions a bug with a time reference: "3 hours ago", "last night", "yesterday's deploy", "this morning"
- User references a specific version: "v2.4.1", "release-2024-01", tag name
- User shares an error log with a timestamp
- User suspects a recent change introduced a bug but current code looks fine
- Deployment errors - user says "deploy failed" or "production is down" with a version/timestamp reference
When NOT to Use
- New feature development
- Refactoring without bug context
- Bug clearly in current code (user says "just broke after my last commit")
Workflow
1. Resolve the Target Commit
Extract temporal clues from the user's message and resolve to a commit hash:
| Clue Type | Git Command |
|---|---|
| Explicit commit hash | Use directly |
Git tag / version (e.g., v2.4.1) |
git rev-list -1 v2.4.1 |
| Relative time (e.g., "3 hours ago") | git log --before="3 hours ago" -1 --format="%H" |
| ISO date (e.g., "2024-01-15") | git log --before="2024-01-15" -1 --format="%H" |
| "last night" / "yesterday" | git log --before="yesterday 23:59" -1 --format="%H" |
For deployment errors:
- If user mentions a release version (e.g., "deploy of v2.4.1 failed"), use the tag
- If user mentions a branch (e.g., "release/v2.4 branch"), use the branch tip
- If user says "current production deploy", check if there's a
productionormainbranch deployed
If multiple conflicting clues, ask the user which to use. If user gives explicit commit hash, use it directly — no resolution needed.
Store the resolved hash as TARGET_COMMIT.
2. Create Isolated Historical Workspace
Create a git worktree at the target commit. This is read-only, isolated,
and doesn't touch the user's working directory.
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 · 199 lines · 77 tokens per session scan A ad2ac70e22c5
temporal-debug is a skill published in the GitHub repository MeherBhaskar/temporal-debug-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 2,071 once invoked, about $0.0004 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
prospec-verify
Verify Implementation - Run 5+1 dimension audit (tasks, spec compliance, constitution, knowledge-implementation consistency, tests, design consistency) and assign quality grade (S/A/B/C/D). Triggers: verify, audit, quality check, 驗證, 稽核, 品質檢查, 評級.
prospec-archive
Archive Changes - Archive completed changes, generate summary, sync requirements to feature specs, and gate archiving on Knowledge sync. Triggers: archive, spec sync, finalize change, 封存, 歸檔, 收尾, 規格同步.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.
release
Cut a prospec GitHub release — bump version strings, tag, and publish release notes in the established format so the Release Binaries workflow attaches multi-platform binaries. Triggers: release, publish release, cut a release, ship a version, 發布, 發佈, 出版本, 發版, 版本發布, 發布 release.
submit-pr
Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.
submit-issue
Open a prospec GitHub issue in the house format — conventional-commit title, Traditional Chinese body (problem → solutions → acceptance criteria), downstream-compatibility block, series cross-links, and optional model-routing guidance. Triggers: submit issue, open issue, create issue, file issue, 開 issue, 發 issue, 建…