Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JansenAnalytics/claudexnpx agentmods add skills/jansenanalytics/claudex/git-bisect-autoWrote 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/jansenanalytics/claudex/git-bisect-auto)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/git-bisect-auto"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/git-bisect-auto/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/jansenanalytics/claudex/git-bisect-auto"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/git-bisect-auto.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 | $0.00040 | $0.00696 |
| Opus 5.5 | $0.00016 | $0.00278 |
| Sonnet 5.5 | $0.00008 | $0.00139 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
git-bisect-auto 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 2mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-bisect-auto
Automated git bisect to find the exact commit that introduced a bug. Run a test command against each bisect step, report the first bad commit with full context.
When to Use
- A regression was introduced and you need to find which commit caused it
- Narrowing down bug introductions in large commit ranges
- Automating binary search through git history
- Generating regression reports for issues/PRs
Scripts
auto-bisect.sh
Automated git bisect runner with safety features.
# Find which commit broke the tests
bash scripts/auto-bisect.sh --good v1.0 --bad HEAD --test "npm test"
# Find which commit introduced a file
bash scripts/auto-bisect.sh --good abc123 --bad def456 --test "test ! -f bug.txt"
# Find which commit broke compilation
bash scripts/auto-bisect.sh --good main~20 --bad main --test "make build"
Features:
- Stashes uncommitted changes before starting, restores after
- Runs
git bisect start, sets good/bad, thengit bisect run - After completion: shows first bad commit, author, date, message, diff stats, changed files
- Cleans up bisect state even on failure
Test command convention: Exit 0 = good (no bug), exit non-zero = bad (bug present). Exit 125 = skip (untestable commit).
bisect-test-gen.sh
Generate ready-to-use test scripts for common bisect scenarios.
# Does it compile?
bash scripts/bisect-test-gen.sh --type compile --params "make build"
# Does a specific test pass?
bash scripts/bisect-test-gen.sh --type test --params "pytest tests/test_auth.py"
# Does the server start (and respond)?
bash scripts/bisect-test-gen.sh --type server --params "npm start,http://localhost:3000,5"
# Does a URL return 200?
bash scripts/bisect-test-gen.sh --type http --params "http://localhost:3000/api/health"
# Does output contain/not contain a string?
bash scripts/bisect-test-gen.sh --type grep --params "npm run build,error,invert"
Output: executable test script written to bisect-test.sh.
regression-report.sh
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.
- 2mo ago First seen · 86 lines · 40 tokens per session scan A 52e9462cad00
git-bisect-auto is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 696 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 2026-09-03.
git-bisect-auto compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-bisect-autoJansenAnalytics/claudex | Skill | 5 | 4mo ago | MIT | A | 40 | Claude Code, Codex |
| advanced-git-rebase-bisect-worktreerondoflow/rondoflow | Skill | 29 | 4d ago | MIT | C | 66 | Claude Code, Codex |
| agenttrace-session-auditsickn33/agentic-awesome-skills | Skill | 49k | 2d ago | MIT | A | 34 | Claude Code |
| git-advanced-workflowswshobson/agents | Skill | 42k | today | MIT | A | 54 | Claude Code |
| agent-merge-conflict-arbiterNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 19 | Claude Code, Codex |
| resolve-handoffomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 23 | Claude Code, Codex |
| reproduce-and-fix-issuesbacknotprop/pstack | Skill | 3.8k | yesterday | MIT | A | 48 | Claude Code, Cursor |