Agentic-Agile Template is a development methodology and starter template for building software through structured collaboration between people and AI coding agents. Development teams use it to organize backlogs, write detailed specifications, coordinate parallel agent work, govern changes, and measure the process. The catalogue entries encode parts of this methodology as instructions and rules.
Borrowing it
Nothing to install: this file belongs to microsoft/agentic-agile-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/agentic-agile-template/main/.github/skills/agentic-agile-forensic-ingest/SKILL.mdgit clone --depth 1 https://github.com/microsoft/agentic-agile-templateWrote 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/microsoft/agentic-agile-template/agentic-agile-forensic-ingest)<a href="https://agentmods.dev/skills/microsoft/agentic-agile-template/agentic-agile-forensic-ingest"><img src="https://agentmods.dev/badge/skills/microsoft/agentic-agile-template/agentic-agile-forensic-ingest/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/microsoft/agentic-agile-template/agentic-agile-forensic-ingest"><img src="https://agentmods.dev/badge/skills/microsoft/agentic-agile-template/agentic-agile-forensic-ingest.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 | $0.00059 | $0.01348 |
| Opus 5.5 | $0.00024 | $0.00539 |
| Sonnet 5.5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
agentic-agile-forensic-ingest 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic-Agile Forensic Ingest
Analyze immutable Git evidence without changing history, render evidence-backed Agentic-Agile issue drafts, and optionally publish verified records to GitHub.
When to Use This Skill
- Reconstruct delivered work from a repository that did not retain its backlog.
- Inspect commits added upstream since a fork's last verified ingest.
- Record unsynced upstream work as an open fork decision record.
- Record incorporated upstream work as closed historical evidence.
- Identify fork-only product changes that may merit a human-led upstream contribution while suppressing process/governance overlays.
Prerequisites
- Python 3.9 or later, using only the standard library.
- Git 2.45 or later available on
PATH. - GitHub CLI (
gh) authenticated only when runningpublish-github. - A clean understanding of the source ref, fork ref, and initial immutable baseline.
- On POSIX, administrator provisioning of the shared lock directory before
publish-github --execute; see the publication-state contract.
Safe Workflow
- Copy and customize
templates/config.example.jsonandtemplates/state.example.json. - Run
analyze, thenvalidatethe deterministic run manifest before rendering or publication. - Run
renderand inspect every draft. Rendering does not contact GitHub. - Run
publish-githubwithout flags to review the local dry-run plan, then add--executeonly after human approval. It is the only operation allowed to contact GitHub or advance state. - Run
recommend-upstream-contributionseparately. Treat its output as a recommendation for humans, never permission to create an upstream branch, pull request, or message.
python scripts/forensic_ingest.py analyze --config <config> --state <state> --output <manifest>
python scripts/forensic_ingest.py validate --config <config> --manifest <manifest> --state <state>
python scripts/forensic_ingest.py render --manifest <manifest> --output <drafts>
python scripts/forensic_ingest.py publish-github --config <config> --manifest <manifest> --drafts <drafts> --state <state> --publication-state <publication-state> [--execute]
python scripts/forensic_ingest.py recommend-upstream-contribution --config <config> --output <report>
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitattributes 9 B
- .gitignore 23 B
- references/evidence-model.md 6.4 KB
- references/issue-lifecycle.md 3.8 KB
- references/manifest-schema.md 13 KB
- scripts/forensic_ingest_lib.py 136 KB runs code
- scripts/forensic_ingest.py 4.5 KB runs code
- templates/config.example.json 762 B
- templates/historical-epic.md 588 B
- templates/historical-story.md 367 B
- templates/state.example.json 180 B
- templates/upstream-decision.md 938 B
- tests/test_analysis.py 83 KB runs code
- tests/test_hardening.py 12 KB runs code
- tests/test_publication.py 82 KB runs code
- tests/test_recommendations_and_cli.py 13 KB runs code
- tests/test_support.py 5.1 KB runs code
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 · 121 lines · 59 tokens per session scan A 1ceea1ba4363
agentic-agile-forensic-ingest is a skill published in the GitHub repository microsoft/agentic-agile-template (98 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,348 once invoked, about $0.0002 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 2026-10-23.
Other skills, from other repositories
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.