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 rampstackco/claude-skills --skill after-action-reportgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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/rampstackco/claude-skills/after-action-report)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/after-action-report"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/after-action-report/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/rampstackco/claude-skills/after-action-report"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/after-action-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.02231 |
| Opus 5 | $0.00069 | $0.01115 |
| Sonnet 5 | $0.00028 | $0.00446 |
| Haiku 4.5 | $0.00014 | $0.00223 |
Grade A, and why
after-action-report 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- after-action-report — 91% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After-Action Report
Run a structured retrospective on a launch, incident, or completed project. Produce actionable lessons, not just a document.
This skill is for after-the-fact analysis. For active incident response, use incident-response. For planning launches, use launch-runbook.
When to use
- After any incident (any severity)
- After every major launch
- At the end of a project (sprint retro, quarterly retro, project closeout)
- When a recurring issue has happened enough times to demand investigation
- When a decision didn't work out and the team wants to learn
When NOT to use
- During an active incident (use
incident-response) - For pre-launch planning (use
launch-runbook) - For one-off bug fixes that don't merit broad analysis
Required inputs
- The event being analyzed (incident, launch, project)
- A timeline reconstructed from logs, chat, tickets
- Participant accounts of what they observed and did
- Outcomes and impact (what actually happened to users, the business)
The framework: blameless analysis
The most important principle: blameless. Without it, retrospectives produce hidden information and theatrical lessons rather than real ones.
What blameless means
- Focus on systems, not individuals
- Assume everyone made reasonable decisions given what they knew at the time
- The question is "why was this decision reasonable to make?" not "who screwed up?"
- Fixing the system means the next person in that situation succeeds where this person didn't
What blameless does not mean
- No accountability (action items still have owners)
- No hard truths (sometimes the system is broken in obvious ways)
- No standards (some patterns of failure are individual, not systemic)
- No discomfort (real reflection is uncomfortable)
The framework: 6 sections
A complete AAR covers six sections.
1. Summary
A 2 to 3 paragraph overview. Captures:
- What happened
- Impact (users, business, time)
- Root cause (in plain language)
- Top action items
What ships with it
1 file 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.
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.
- 9d ago First seen · 289 lines · 139 tokens per session scan A 97c20ae6885f
after-action-report is a skill published in the GitHub repository rampstackco/claude-skills (830 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 2,231 once invoked, about $0.0007 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
mass-ulw
Drives dependency-ordered child work through the native workflow tool, one run per phase with retry/amend/send recovery. Use when the user asks for mass-ulw, a DAG of tasks, or fan-out work where some tasks must wait on others.
suede-ops-architecture
Suede-owned operations-architecture discipline that fixes the shape of a system before anyone builds it: entity schema first, exactly one write path per entity, every unit of work routed to a deterministic automation, an AI agent, or a human decision, every existing tool marked absorb, keep, or kill, and the build…
suede-ops-assessment
Suede-owned operations-assessment discipline that maps how work actually happens before anyone designs a system: floor-level interviews with the people who do the work, an inventory of every silo including spreadsheets and inboxes used as databases, friction quantified in the requester's own numbers, opportunities…
github-triage
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only.…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
multi-agent-client-onboarding
Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter. Real consulting workflow that produces a complete client assessment.