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 ulises-jeremias/agent-toolkit --skill project-assessmentgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/project-assessment)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/project-assessment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/project-assessment/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/ulises-jeremias/agent-toolkit/project-assessment"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/project-assessment.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 | $0.00043 | $0.01067 |
| Opus 5.5 | $0.00017 | $0.00427 |
| Sonnet 5.5 | $0.00009 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
project-assessment 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Assessment (WHAT)
Use this skill when the user asks for a project assessment, maturity assessment, delivery audit, technical assessment, management assessment, quality indicator review, or improvement roadmap.
This is a router skill. Keep it focused on assessment flow, gates, and delegation. Use the unit-specific skills for scoring details.
Default guardrails
- Apply
output-handshakebefore producing any final assessment report, scorecard, action plan, or executive summary: ask where the artifact should live and confirm human review. - Apply
project-assessment-evidencebefore scoring. Evidence may live in repositories, boards, docs, spreadsheets, dashboards, incidents, PRs, meetings, interviews, Slack, emails, or any other project system. Ask the user where to find each source. - Never assign a score without evidence. If evidence is missing, mark the indicator as Not assessed or score it with Low confidence and state the assumption explicitly.
- Keep sensitive details out of reusable artifacts. Redact secrets, credentials, private customer data, and unnecessary personal data.
- Do not mention client-specific reference examples or internal audit links in generated outputs. Use only abstracted patterns.
Assessment flow
- Intake
- Ask the assessment purpose: baseline, periodic review, due diligence, quality improvement, delivery health check, AI-readiness review, or internal audit support.
- Ask the assessment period and target audience.
- Ask whether the assessment should cover management units, technical units, or both.
- Ask which repositories, products, squads, platforms, or delivery scopes form each assessment unit.
- Evidence collection
- Delegate to
project-assessment-evidence. - Build an evidence map before scoring.
- Ask the user where each evidence category lives instead of assuming ClickUp or repository-only evidence.
- Delegate to
- Unit assessment
- For technical workloads, delegate to
technical-unit-assessment. - For project management and delivery scopes, delegate to
management-unit-assessment. - If UI depth is required, pair the technical unit assessment with
figma/figma-implement-design. - If repository discovery is required, pair with
assistantand the repository-specific rules.
- For technical workloads, delegate to
- Consensus and scoring
- Use the 1 to 5 maturity scale from the assessment indicators.
- Treat score 3 as "defined or partially mature", not as average performance.
- Record confidence per score: High, Medium, Low, or Not assessed.
- For subjective indicators, ask who should validate the score and whether weights are needed.
- Findings and action plan
- Summarize strengths, risks, gaps, and opportunities.
- Separate confirmed findings from assumptions and missing evidence.
- Convert recommendations into actionable follow-ups only after user approval, delegating ticket creation to the relevant ticket skill.
What ships with it
2 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.
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 · 91 lines · 43 tokens per session scan A 4825e39ced22
project-assessment is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,067 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 2026-09-04.
Other skills, from other repositories
github-navigator
GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any github.com URL or GitHub repo path like owner/repo. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR'…
create-jira-item
Create Jira issues (stories, epics, initiatives) with custom field introspection to fill org-specific fields correctly. Use when the user asks to create a Jira ticket, story, epic, initiative, or task.
implement-plan
Use when the user wants to execute an approved implementation plan and says any of "do it" (with a plan in scope), "lets do it" / "let's do it", "confirmed" (as approval to proceed on a plan), "implement the plan", "implement this", "execute the plan", "start implementing", "work through the plan", "implement the next…
breaking-down-work
Decomposes a goal, feature, epic, or deliverable into a structured task tree (tasks, subtasks, checklists) with dependencies in Astravue. Use when the user wants to break down, decompose, or plan out work, turn an epic or feature into tasks, "split this into tasks", scope a deliverable, or build a work breakdown…
capturing-meeting-actions
Extracts action items from meeting notes, transcripts, or a brain dump and creates them as owned, dated tasks in Astravue. Use when the user pastes meeting notes or a transcript, asks to turn notes or standup discussion into tasks, capture action items, or "make tasks out of this".
mapping-dependencies
Maps task dependencies in an Astravue project, finds the critical path and blocked work, and detects circular dependencies before any rescheduling. Use when the user asks about dependencies, blockers, what's blocking what, the critical path, or wants to understand or fix the sequencing of a project.