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 toejough/engram --skill bisect-before-fixgit clone --depth 1 https://github.com/toejough/engramWrote 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/toejough/engram/bisect-before-fix)<a href="https://agentmods.dev/skills/toejough/engram/bisect-before-fix"><img src="https://agentmods.dev/badge/skills/toejough/engram/bisect-before-fix/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/toejough/engram/bisect-before-fix"><img src="https://agentmods.dev/badge/skills/toejough/engram/bisect-before-fix.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 | $0.00077 | $0.00992 |
| Opus 5.5 | $0.00031 | $0.00397 |
| Sonnet 5.5 | $0.00015 | $0.00198 |
| Haiku 4.5 | $0.00008 | $0.00099 |
Grade A, and why
bisect-before-fix 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 28d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bisect Before Attributing: Isolate Pre-Existing Regressions from Change-Caused Failures
Overview
When a trap/eval gate returns RED on your branch, it names a failure and often suggests a fix. But the regression might be pre-existing (a bug introduced in an earlier commit) rather than caused by your change. Applying a fix to a pre-existing failure masks the real issue, hides a regression that belongs in its own issue, and mislabels the cause. This skill is the bisection procedure that isolates the cause before any fix is applied.
When to Use
A trap/eval gate (gate.py, crowded_gate.py, or similar) has returned RED on the current HEAD of a branch or change under review. You have a suggested fix and pressure (time, deadline, authority, false confidence) to apply it immediately without verification. Triggers include:
- Gate returns RED with a suggested fix ("use X at line Y")
- You are under pressure (time window, deadline, peer confidence) to merge now
- Authority figure says "we know what this is, just apply the fix"
- Peer says "I've seen this pattern, the fix works every time"
- You feel confident the change caused it
Procedure
- Identify the commit immediately preceding the change under review's relevant commits.
- Check out that preceding commit.
- Rebuild the artifact under test from that commit.
- Re-run the identical gate (e.g.
gate.py --tier smoke) against that rebuilt artifact. - Compare this verdict to the original RED verdict observed on the change under review's HEAD.
- If the same failure reproduces on the pre-change commit: the change under review is NOT the cause -- do not apply its prescribed fix; instead file the pre-existing regression as its own separate issue for dedicated investigation.
- If the failure does NOT reproduce on the pre-change commit: the change under review is confirmed as the cause -- its prescribed fix (if any) applies.
- Restore the original HEAD/branch and rebuild the artifact before reporting results.
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.
- 28d ago First seen · 54 lines · 77 tokens per session scan A dc26cd7d8452
bisect-before-fix is a skill published in the GitHub repository toejough/engram (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 992 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 2026-09-21.
Other skills, from other repositories
code-task
PREFERRED way to change code in a REAL repository: fix a GitHub issue, fix a bug, add/implement a function or feature, or make any edit to a project the user names by a filesystem path (e.g. /tmp/foo, /code/bar) or a git URL. Clones the repo, runs an OpenSquilla agent on the host to make the change on a task branch…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
Docker Management
Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.
SongSee
Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.