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 agentmods add skills/fusebase-dev/fusebase-flow/git-history-diagnosticnpx skills add fusebase-dev/fusebase-flow --skill git-history-diagnosticgit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWhat 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 | $0.00100 | $0.01550 |
| Opus 5 | $0.00050 | $0.00775 |
| Sonnet 5 | $0.00020 | $0.00310 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
git-history-diagnostic 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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git History Diagnostic
Style: Mode-B-lite.
Purpose
Regression archaeology: when behavior that previously worked is now broken, locate where it broke by comparing commits / bisecting history — so the fix targets the actual causing change, not a guess. Read-only diagnosis; the fix is handed to zoom-out + validation-and-qa.
When to invoke
- "It used to work" / "this is a regression" / "when did X break".
- A test that passed at an earlier commit now fails.
- Operator points to a known-good prior state and a now-broken current state.
Do not invoke when
- The behavior never worked (net-new bug → normal debugging).
- Routine rollback of a known commit →
workflows/git-discipline.md. - Reproduction isn't established yet → run FR-10 reproduce-before-fix first (you need a reliable signal to bisect against).
Required inputs
| Input | Where it lives | If missing |
|---|---|---|
| A reliable broken/works signal (test or repro) | test suite / repro steps | establish via FR-10 first; bisecting needs a yes/no test |
| Last-known-good reference (commit/tag/date) | operator / git history | search backward from HEAD for the transition |
| Current broken state | HEAD | — |
Procedure
- Pin the signal. Define a deterministic check that returns good/bad (a test command, a repro). Bisection is only as reliable as this signal.
- Bracket. Identify a known-good commit (or tag/date) and a known-bad commit (usually HEAD). Verify the signal at both ends.
- Bisect. Narrow the range with
git bisect runon the pinned signal (see § Bisect mechanics; manualgood/badstepping or binary search when the signal is not scriptable) until the first bad commit is found. - Explain. Show that commit's diff; identify the specific change that introduced the regression (file:line).
- Hand off. Pass the finding to
zoom-out(root-cause vs revert decision) andvalidation-and-qafor the fix + regression test. Do not fix here. - Capture. If the regression class is recurring, note it in
docs/problem-catalog/.
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.
- 2d ago First seen · 115 lines · 100 tokens per session scan A c6d7cb33a4c6
git-history-diagnostic is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 100 tokens to every session and 1,550 once invoked, about $0.0005 per session on Opus 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
adobe-express-core
Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.
adobe-express-monetization
Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.
adobe-express-spectrum-ui-ux
Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…
adobe-express-cors-and-backend
Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…
adobe-express-document-manipulation
Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.
adobe-express-oauth-authentication
Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.