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 mostafa-drz/claude-skills --skill repo-timelinegit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/repo-timeline)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/repo-timeline"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/repo-timeline/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/mostafa-drz/claude-skills/repo-timeline"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/repo-timeline.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 | $0.00067 | $0.02768 |
| Opus 5.5 | $0.00027 | $0.01107 |
| Sonnet 5.5 | $0.00013 | $0.00554 |
| Haiku 4.5 | $0.00007 | $0.00277 |
Grade A, and why
repo-timeline 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 1mo 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Timeline
Visualize the history of a repository or branch as a meaningful, grouped timeline — not raw git log, but an engineer-friendly narrative of what changed, when, and why.
Preferences
On startup, use the Read tool to load ~/.claude/skills/repo-timeline/preferences.md. If it doesn't exist, use defaults.
Context
On startup, use Bash to detect: current git branch, repo root (git rev-parse --show-toplevel), repo name (basename $(git rev-parse --show-toplevel)), remote URL (git remote get-url origin), and GitHub repo name (gh repo view --json nameWithOwner -q .nameWithOwner). Skip any that fail.
Command routing
Check $ARGUMENTS:
help→ display help then stopconfig→ interactive setup then stopreset→ delete~/.claude/skills/repo-timeline/preferences.md, confirm, stop- branch name — if argument looks like a branch name (no
--prefix), use it as the target branch - flags — parse
--since,--until,--focus,--depth,--sources - empty — use current branch with defaults
Flags
Parse from $ARGUMENTS:
--since <time>— start of time range (e.g., "2 weeks ago", "2026-01-01", "last tag")--until <time>— end of time range (defaults to now)--focus <areas>— comma-separated paths or areas to emphasize (e.g., "api,auth,frontend")--depth brief|detailed— "brief" for one-liners, "detailed" for full descriptions (default from preferences)--sources <list>— comma-separated sources: git, github, linear, changelog (default: all available)
Help
Repo Timeline — Engineer-friendly timeline of repository changes
Usage:
/repo-timeline Current branch, full history
/repo-timeline feature/auth Specific branch
/repo-timeline --since "2 weeks ago" Time-bounded timeline
/repo-timeline --focus "api,auth" Focus on specific areas
/repo-timeline --depth brief One-liners only
/repo-timeline --depth detailed Full descriptions with context
/repo-timeline --sources git,github Only specific sources
/repo-timeline config Set preferences
/repo-timeline reset Clear preferences
/repo-timeline help This help
Flags:
--since <time> Start of time range (e.g., "1 month ago", "v2.0.0")
--until <time> End of time range (default: now)
--focus <areas> Comma-separated paths/areas to emphasize
--depth brief|detailed Level of detail (default: from preferences)
--sources <list> Sources to use: git, github, linear, changelog
Examples:
/repo-timeline Full timeline of current branch
/repo-timeline main --since "last month" Main branch, last month
/repo-timeline --focus "src/api" --depth detailed
/repo-timeline --since "v1.0.0" --until "v2.0.0" Between releases
/repo-timeline develop --sources git,github
Current preferences:
(read from preferences.md)
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.
- 1mo ago Changed · +2 lines 645d4de197c3
- 1mo ago First seen · 290 lines · 67 tokens per session scan A f465c233436c
repo-timeline is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 2,768 once invoked, about $0.0003 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
rudder-import-and-evolve
Imports existing RudderStack workspace resources into YAML files for git-based management. Use when importing existing RudderStack resources to CLI management and evolving them safely.
iterate
Diverge-converge workflow: spin up N agents on isolated worktrees, each exploring a different approach to the same problem. Compare results side-by-side (with optional preview ports), pick a winner, merge it back. Use when the user says /iterate, 'try multiple approaches', 'explore different directions', or wants to…
vienen-las-visitas
Use before work crosses to another person or system — opening a pull request, pushing a shared branch, requesting review, handing off to another agent, a demo, or a release. NOT for ordinary intermediate commits; this is the boundary-crossing gate, not a per-commit ritual.
bootstrap-project
Use when setting up a new project with the full opinionated workflow — session memory, commit hooks, copyright headers, ROADMAP, and CLAUDE.md. Invoke with "bootstrap project", "setup project", "new project setup", or /bootstrap-project.
session-end
Use when the user says "end session", "wrap up", "let's stop here", or invokes /session-end.
visual-explainer-diff
Use when asked to visualize, explain, or document what changed between two git refs in a codebase. Triggers: 'show what changed in this PR', 'visualize the diff', 'explain the changes between main and this branch', 'generate a change report', 'what did this commit change architecturally', or any request to understand…