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 ArabelaTso/Skills-4-SE --skill bisect-aware-instrumentationgit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/bisect-aware-instrumentation)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/bisect-aware-instrumentation"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/bisect-aware-instrumentation/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/arabelatso/skills-4-se/bisect-aware-instrumentation"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/bisect-aware-instrumentation.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 | $0.00087 | $0.02229 |
| Opus 5 | $0.00044 | $0.01115 |
| Sonnet 5 | $0.00017 | $0.00446 |
| Haiku 4.5 | $0.00009 | $0.00223 |
Grade C, and why
bisect-aware-instrumentation scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/test_cache How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bisect-Aware Instrumentation
Overview
Instrument code to support efficient git bisect operations by producing deterministic pass/fail signals and concise runtime summaries. This skill helps create robust test scripts that work reliably with git bisect run, handling edge cases like flaky tests, build failures, and non-deterministic behavior.
Core Workflow
1. Understand the Regression
Before instrumenting, clarify:
- What behavior changed? (bug introduced, performance regression, test failure)
- What is the "good" commit? (known working state)
- What is the "bad" commit? (known broken state)
- How to reproduce the issue? (test command, manual steps)
2. Create Bisect Test Script
Generate a test script that returns proper exit codes for git bisect:
Exit Code Convention:
0: Good commit (test passes)1-124, 126-127: Bad commit (test fails)125: Skip commit (cannot test - build failure, missing dependencies)
Template:
#!/bin/bash
# bisect_test.sh - Test script for git bisect run
set -e # Exit on error
# Build/setup phase
if ! make build 2>/dev/null; then
echo "SKIP: Build failed"
exit 125
fi
# Run test with timeout
timeout 30s ./run_test || TEST_RESULT=$?
# Interpret results
if [ $TEST_RESULT -eq 0 ]; then
echo "GOOD: Test passed"
exit 0
elif [ $TEST_RESULT -eq 124 ]; then
echo "SKIP: Test timeout"
exit 125
else
echo "BAD: Test failed with code $TEST_RESULT"
exit 1
fi
3. Add Determinism Safeguards
Handle non-deterministic behavior:
Retry Logic for Flaky Tests:
# Run test multiple times to confirm
PASS_COUNT=0
for i in {1..3}; do
if ./run_test; then
((PASS_COUNT++))
fi
done
if [ $PASS_COUNT -eq 3 ]; then
echo "GOOD: All 3 runs passed"
exit 0
elif [ $PASS_COUNT -eq 0 ]; then
echo "BAD: All 3 runs failed"
exit 1
else
echo "SKIP: Flaky test ($PASS_COUNT/3 passed)"
exit 125
fi
Environment Isolation:
# Clean state before each test
rm -rf /tmp/test_cache
export RANDOM_SEED=42
export TZ=UTC
What ships with it
4 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.
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.
- 12d ago First seen · 367 lines · 87 tokens per session scan C 3e035e6489a6
bisect-aware-instrumentation is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 21d ago), licensed Apache-2.0. It adds 87 tokens to every session and 2,229 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
steward
Drive a pull request on this repository to green — which fast checks to run before pushing, how to read a red check, and what to do about a review comment. Use when a CI failure, a review comment, a merge conflict, or a scheduled check-in arrives on a PR you opened or were asked to drive.
morning
Use when the user says "/nightshift:morning", "what happened overnight", "how did the night go", "why did the loop stop", or opens a session in a repo with a loop/ directory after a scheduled run. Reads the journal since the last start line and every open land / land:blocked pull request, says per stop what happened…
ss-troubleshooting-workflow
End-to-end defect fix — takes an issue link, alert ID, or problem description and orchestrates tier-adaptive root-cause investigation, human confirmation, branching, a fix plan, multi-agent coding with built-in review, and PR/commit delivery. Use only when the user explicitly asks for the full diagnose-to-delivery…
review-change
Review a completed change against its authorizing spec in fresh context — evidence-based checks, severity-ranked findings, and a written verdict for the human's merge decision. Use when a diff needs reviewing before merge, or when add-feature / fix-bug / implement-spec reaches its review gate.
open-world-design
Use when designing, generating, or reviewing the spatial side of an open world — macro-layout and terrain, landmarks and sightlines, biome identity, verticality, navigation/wayfinding, signal color, exploration pull, and spatial pacing (the wonder→fear gradient, tension/release). Also use to diagnose a world that…
Framework Upgrader
Drives a major-version framework bump as a sequence of small, reversible, CI-gated PRs using official codemods and changelog diffing while keeping the app green. Use when bumping React, Rails, Spring Boot, Angular, or any framework across a major version with breaking API/config changes; do NOT use for language or…