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 TalonT-Org/AutoSkillit --skill pipeline-summarygit clone --depth 1 https://github.com/TalonT-Org/AutoSkillitWrote 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/talont-org/autoskillit/pipeline-summary)<a href="https://agentmods.dev/skills/talont-org/autoskillit/pipeline-summary"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/pipeline-summary/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/talont-org/autoskillit/pipeline-summary"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/pipeline-summary.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 | $0.00032 | $0.01295 |
| Opus 5.5 | $0.00013 | $0.00518 |
| Sonnet 5.5 | $0.00006 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
pipeline-summary 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Summary
Create a GitHub issue documenting bugs encountered during a pipeline run and a PR from the feature branch into the target branch.
Arguments
/autoskillit:pipeline-summary {bug_report_path} {feature_branch} {target_branch} {workspace} [{closing_issue}]
- bug_report_path — Path to the JSON file containing bug metadata
- feature_branch — Name of the branch containing all accumulated fixes
- target_branch — Branch to create the PR against (e.g., "main")
- workspace — Path to the git repository workspace
- closing_issue — (Optional) GitHub issue number whose
## Requirementssection should be extracted and embedded in the PR body. When absent or empty, requirements extraction is skipped.
When to Use
- End of a pipeline run with
collect_on_branchenabled - Any pipeline that accumulates fixes on a feature branch and needs a summary
Critical Constraints
NEVER:
- Fail the pipeline if
ghis not available or not authenticated — write a local summary instead - Create empty issues or PRs (skip if no bugs to report)
- Modify any source code — this skill only creates GitHub artifacts and a summary file
ALWAYS:
- Check
gh auth statusbefore attempting GitHub operations - Push the feature branch before creating the PR
- Write a local summary markdown file regardless of GitHub availability
- Output
summary_path=<path>for capture by the orchestrator - If GitHub operations succeed, also output
issue_url=<url>andpr_url=<url>
Workflow
Step 1: Parse Arguments
Parse up to five positional arguments from the prompt. The fifth (closing_issue) is optional.
Step 2: Read Bug Report
Read the JSON file at {bug_report_path}. Expected structure:
[
{
"step": "string — pipeline step where failure occurred",
"error": "string — error description",
"fix": "string — what was done to fix it",
"iteration": "number — which bugfix iteration"
}
]
If the file is empty, contains [], or doesn't exist, write a clean-run summary and exit successfully.
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 · 139 lines · 32 tokens per session scan A 62297b56129a
pipeline-summary is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,295 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 2026-09-03.
Other skills, from other repositories
task-start
Start work on an EXISTING work item with Baron — load it, cut its canonical branch, move it to inprogress, and sync the local checkout. Use when the user says to start/pick up/resume a known task, bug, or story (by id, key, or URL). To create a new item first, use task-new.
task
Create one or more tasks via wade task create — for a single bug/feature OR a full plan/PRD breakdown. This is the STANDALONE task-creation workflow, used whenever the user directly asks to create a task/issue outside a wade plan session. Assesses scope, proposes a single- or multi-issue breakdown with reasoning, gets…
feedback-fix-review
Review feedback-driven corrections for verified defects and direct regressions.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
resolve-handoff
Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.