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 yeaight7/agent-powerups --skill regression-bisectinggit clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/regression-bisecting)<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/regression-bisecting"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/regression-bisecting/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/yeaight7/agent-powerups/regression-bisecting"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/regression-bisecting.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 | $0.00023 | $0.00686 |
| Opus 5.5 | $0.00009 | $0.00274 |
| Sonnet 5.5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
regression-bisecting 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
When a feature used to work but is now broken, do not guess what broke it. Use binary search through git history to find the exact commit, then read the root cause out of that commit's diff.
When to Use
- A regression appeared and the offending commit is unknown
- A bug is reported "since some release" with a wide commit range
- A deterministic repro command exists or can be built
Inputs
- A test command that returns exit code
0if good and non-zero if bad (e.g.,npm run test:reproornode repro.js) - A known-good ref and a known-bad ref (typically
HEAD)
Workflow
-
Define the test. You must have a single command that returns exit code
0if good, and non-zero if bad. If none exists, build one first (seeminimal-reproduction). -
Find a known good state. Ask the user or search git history for a commit where you are certain the feature worked (a release tag is a good candidate). Verify it by running the test on it.
-
Find the known bad state. Typically
HEAD. -
Bisect automatically:
git bisect start <bad> <good> git bisect run npm run test:repro # or: git bisect run node repro.js git bisect log # record of the search git bisect reset # always return to the original refgit bisect runchecks out each midpoint and runs the command until it isolates the first bad commit. Usegit bisect skipfor midpoints that fail to build. For workflows wherebisect runis not viable, manually check out the midpoint commit, run the test, and narrow the window withgit bisect good/git bisect bad. -
Analyze the offending commit. Once the exact commit is found, use
git show <commit>to analyze the diff. The root cause is contained entirely within that diff.
Output
- The first bad commit (hash + subject) and the bisect log
- A root-cause explanation grounded in that commit's diff
Verification
- Test command verified deterministic (0/non-zero) before bisecting started
- Known-good ref actually tested as good, not assumed
-
git bisect resetrun afterward — repo back on the original ref - Root cause explained from the offending diff, not just the commit named
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 First seen · 60 lines · 23 tokens per session scan A 9501c87667b7
regression-bisecting is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 19d ago), licensed Apache-2.0. It adds 23 tokens to every session and 686 once invoked, about $0.0001 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 2026-09-14.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
github-auth
GitHub auth setup: HTTPS tokens, SSH keys, gh CLI.
github-repo-management
Clone, create, fork repos; manage remotes, releases.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.