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 commands/sunbird-knowlg/knowledge-platform-jobs/commitgit clone --depth 1 https://github.com/Sunbird-Knowlg/knowledge-platform-jobsWrote 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/commands/sunbird-knowlg/knowledge-platform-jobs/commit)<a href="https://agentmods.dev/commands/sunbird-knowlg/knowledge-platform-jobs/commit"><img src="https://agentmods.dev/badge/commands/sunbird-knowlg/knowledge-platform-jobs/commit.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00890 |
| Opus 5 | $0.00005 | $0.00445 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
commit 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 today.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creating a git commit for knowledge-platform-jobs (Scala/Flink/Maven). Extra hint from the user (may be empty): $ARGUMENTS
Pre-loaded context
Status:
!git status --porcelain=v1 -b
Staged diff:
!git diff --staged
Recent commit style (mirror it):
!git log --oneline -12
Steps
- Analyze the changes above and determine the commit type and scope.
- If nothing is staged, propose the files to stage and ask the user before running
git add. Never stage secrets (.env*,*.pem,*.key), and never stage the temporary local-run pom edits (addedflink-clients, commented-outprovidedscope,createLocalEnvironment()). - By default don't stage
.mdfiles — ask the user before including any documentation changes. - If the change touches
jobs-core, remind the user it is duplicated indata-pipelineand likely needs mirroring there. - Present the proposed commit message and wait for confirmation before committing.
- Create the commit with
git commit.
Commit Message Format
{type}({scope}): {short description}
{optional body — only if the change needs explanation}
Types
feat— new feature or job capabilityfix— bug fixrefactor— code restructure without behavior changestyle— formatting only, no logic changetest— adding or fixing testschore— build, config, dependency changesdocs— documentation only
Scope
Use the job/module being changed:
jobs-core— shared Flink base (BaseProcessFunction, BaseJobConfig, serde) — duplicated in data-pipelinepublish— publish-pipeline (knowlg-publish, live-node-publisher, publish-core)content-embedding— content-embedding jobtransaction-event— transaction-event-processor (CDC → Elasticsearch)qrcode— qrcode-image-generatordialcode— dialcode-context-updaterasset-enrichment— asset-enrichment jobvideo-stream— video-stream-generatorcassandra-migration— cassandra-data-migrationbuild— Maven / pom / cloud-profile / dependency changesci— GitHub Actions / CircleCI / SonarCloud workflows
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.
- today First seen · 100 lines · 11 tokens per session scan A 50a63e7cdc64
commit is a command published in the GitHub repository Sunbird-Knowlg/knowledge-platform-jobs (4 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 890 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.