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 joenandez/spectre --skill spectre-rebasegit clone --depth 1 https://github.com/joenandez/spectreWrote 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/joenandez/spectre/spectre-rebase)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-rebase"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-rebase/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/joenandez/spectre/spectre-rebase"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-rebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 34 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00089 | $0.01015 |
| Opus 5 | $0.00044 | $0.00508 |
| Sonnet 5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
spectre-rebase 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rebase
Rebase the current branch onto a target, resolving conflicts and verifying the result, with a recoverable safety net.
Inputs
- Target branch from
$ARGUMENTS(e.g.origin/main) and optional--orchestratedwhen a parent workflow owns the next step. If absent, ask which branch to rebase onto. - Optional
--verification-owner parent, valid only with--orchestrated. It transfers post-rebase verification to the parent; plain--orchestrateddoes not transfer ownership. - Current branch + working-tree state (read just-in-time via
git status, never assume).
Working Set
- The current git branch and its commits ahead of target.
- Project test/lint commands (detect from repo:
npm test,pytest,cargo test,go test).
Outputs + DONE
A rebased branch and a Rebase Summary returned in-thread (not written to disk):
- Branch
{current} → {target}; commit count; conflict count; verification resultPASS|QUALIFIED|PARENT_OWNED|NEEDS_AUTHORITY. - Per-conflict decision table:
| File | Decision | Rationale |. - Smoketest guide grounded in files touched:
{area}: [ ] {behavior to verify}. - Safety line: backup ref name + restore command.
DONE when self-owned: rebase completes with no remaining conflict markers, commit count validates against expectation, affected verification has no branch-caused failure, unrelated findings are routed, and the summary (including the backup ref + restore command) is delivered.
REBASE_READY when parent-owned: rebase completes with no remaining conflict markers, commit count validates against expectation, and the summary records verification: PARENT_OWNED. Parent verification is advisory workflow evidence unless its own contract says otherwise; it is not a precondition for PR creation.
Method / guardrails
- Snapshot first. If the tree is dirty, auto-commit (
git commit -am "chore: snapshot before rebase") — no prompt. Thengit fetch origin. - YOU MUST create a backup ref before rebasing and surface its restore command in the summary:
git branch backup/rebase-$(date +%Y%m%d-%H%M%S)→ restore viagit reset --hard {backup}. This is the only rollback; never start the rebase without it. - Run
git rebase {target}. For each conflict: resolve favoring the target branch's conventions (no prompts), record{file}: {decision} — {rationale},git add,git rebase --continue. Repeat until clean. - Verify after resolution — always confirm commit count and no unexpected changes.
- Self-owned: run affected lint/typecheck/build plus related tests selected from the rebased diff. Repair branch-caused failures and reverify; record/route unrelated failures; use only a failing focused check at the target SHA for indeterminate attribution. Never run a repository-wide baseline or full suite.
--orchestrated --verification-owner parent: do not run lint or tests; returnREBASE_READYwithverification: PARENT_OWNED.
- Track every resolution decision as you go (the summary table is a postcondition, not an afterthought).
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.
- yesterday Changed · +8 lines 94623166b7e7
- 11d ago First seen · 49 lines · 89 tokens per session scan A b5676cc2b619
spectre-rebase is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 1,015 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.