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 omnigentx/jarvis --skill retrospectivegit clone --depth 1 https://github.com/omnigentx/jarvisWrote 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/omnigentx/jarvis/retrospective)<a href="https://agentmods.dev/skills/omnigentx/jarvis/retrospective"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/retrospective/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/omnigentx/jarvis/retrospective"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/retrospective.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 | $0.00021 | $0.00506 |
| Opus 5.5 | $0.00008 | $0.00202 |
| Sonnet 5.5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
retrospective 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 14d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective
Use after an accepted milestone or a significant failure/rework checkpoint. Idle is not completion. A retrospective may happen while delivery remains incomplete; it does not authorize acceptance or a Jira Done transition.
Coordinate a focused discussion
Check existing meetings and Jira for this checkpoint before creating another. Reuse the existing retrospective and action items on retries. Invite only owners involved in the decision; avoid an all-team meeting for a single tool failure.
Use create_meeting(agenda="Retrospective — <checkpoint>", participants="<actual agent names>", description="<evidence links, decision needed>", max_rounds=2).
Get actual names from the current team, not example rosters. The creator is included automatically. Present findings before issuing a separate verdict after participants have contributed or absences are explicitly recorded.
Discuss evidence, root cause, what worked, and one measurable change. Separate observed facts from hypotheses. Publish the summary in Confluence; link actionable Jira tasks with owner, acceptance criteria and measurement. Workspace notes are drafts, not durable memory.
Learn within each agent's scope
Each owner proposes their own reusable lesson through memory_server procedure_propose(title, steps). The tool binds the caller identity: never impersonate another owner or store a team observation as a user preference.
Include in steps:
- Trigger/context where this workflow applies.
- Evidence and root cause; limits of what was actually verified.
- Concrete steps, verification and stopping conditions.
- Jira/Confluence evidence references and review date.
Use one concise procedure per distinct lesson. Search your existing procedural memories first and reuse an equivalent lesson. Do not persist transcripts, temporary assignments, credentials, raw tool dumps or unsupported claims. Cross-agent/global promotion requires separate user review.
A returned candidate ID with pending status means proposed, not learned or applied. Approval is mandatory for procedure proposals. If memory is disabled or unavailable, record the unresolved action on Jira; do not claim persistence.
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.
- 14d ago Changed · -14 lines · +10 tokens per session 3ee54b5ac612
- 1mo ago First seen · 50 lines · 11 tokens per session scan A 4a604036ae7e
retrospective is a skill published in the GitHub repository omnigentx/jarvis (39 stars, last pushed 11d ago), licensed MIT. It adds 21 tokens to every session and 506 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 2026-08-30.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.