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 endorphin-ai/hasbrains-agent-kit --skill docs-project-managementgit clone --depth 1 https://github.com/endorphin-ai/hasbrains-agent-kitWrote 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/endorphin-ai/hasbrains-agent-kit/docs-project-management)<a href="https://agentmods.dev/skills/endorphin-ai/hasbrains-agent-kit/docs-project-management"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/docs-project-management/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/endorphin-ai/hasbrains-agent-kit/docs-project-management"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/docs-project-management.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 | $0.00319 | $0.03201 |
| Opus 5 | $0.00160 | $0.01600 |
| Sonnet 5 | $0.00064 | $0.00640 |
| Haiku 4.5 | $0.00032 | $0.00320 |
Grade A, and why
docs-project-management 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 8d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TASKLANG TYPE SKILL
IDENTITY "Docs Project Management (the docs/-native system of record)"
A universal, reusable playbook for running a whole project — requirements, planning, build tracking, testing, bugs, and team reporting — as committed markdown inside the repo's
docs/folder. It works in ANY project, in any stack, from day one of a NEW project: no external issue tracker, no ticket system, no proprietary tooling. A work item is a markdown file with YAML frontmatter; a relationship is a relative markdown link; a status change is a frontmatter edit; the full history is git.It does three jobs:
- WORK-ITEM MODEL — WHAT document types exist (PRD, TRD, Epic, User Story, Test Case, Bug, Roadmap), WHERE each lives, HOW they link, and HOW status is tracked.
- TEAM WORK-REPORTING — HOW every agent/contributor reports its work so anyone can see, in one committed place, everything that was done (who, what, when, with which evidence).
- DURABLE vs TEMPORARY — WHAT belongs in committed
docs/versus the git-ignored.ai_log/temp-evidence folder, and when to promote content from one to the other.
§1 Document types — WHAT the system manages
Every work item is a committed markdown file in its
docs/subfolder: descriptive kebab-case filename (never an opaque ID), YAML frontmatter for status/metadata, relative-markdown links for relationships. Full field-level detail: [[work-item-taxonomy]].
TABLE document-types
COLUMNS: Type, Lives in, What it is / holds
ROW: Project brief | docs/project_brief.md | The product spec — the SOURCE OF TRUTH the whole project derives from; wins over any assumption
ROW: Project config| docs/project_config/info.md | The single home for project-specific FACTS (product name, app name, stack, domain, scope, success scenarios) — agents read it instead of hard-coding facts
ROW: Roadmap | docs/ROADMAP.md + docs/roadmap.json | The milestone/release plan (human file) + a machine-readable MIRROR of every work item's current status (JSON cache, regenerated from docs/, committed)
ROW: PRD | docs/prd/ | Product Requirements Document — WHAT to build and WHY: objectives, in-scope / out-of-scope, testable acceptance criteria per success scenario
ROW: TRD | docs/trd/ | Technical Requirements Document — HOW to build it: architecture, data model, migrations, jobs, authz. Canonical TRD home; keep index.json (machine registry, one entry per TRD) + index.md (human index) beside the files
ROW: Epic | docs/epics/ | A large feature/theme grouping related User Stories; carries goal + scope + its story list
ROW: User Story | docs/user_stories/ | The smallest shippable requirement — "as a I want " + numbered acceptance criteria; filename NNN-<kebab-title>.md
ROW: Test Case | docs/test_cases/ | A verification script for ONE behavior — numbered navigate→action→expected steps; filename tc-NNN-<kebab-behavior>.md; MUST follow the [[test-case-template]] and link its story "is tested by"
ROW: Bug | docs/bugs/ | A defect AND its Root-Cause-Analysis in ONE file — Symptom/Reproduction + 5-Whys RCA + Preventative Action at detection; Fix/diff/Resolved sections completed by whoever fixes it ([[bug-rca-report]]); blocks its story
ROW: Session report| docs/sessions/-/ | Per-run team work folder — a README manifest + one bookended report per agent/phase ([[session-reporting]])
ROW: Feature log | docs/reports/feature-log.md + feature-log/ | The team work-log split by feature: one lean index row per feature, linking a per-feature file where each run appends a row
RULES
- Filenames: descriptive kebab-case, never opaque IDs. External refs (ticket numbers), when they
exist, go in frontmatter + the title line — not the filename.
- Each subfolder may carry a template_<type>.md seed; new items copy its shape.
- Only APPROVED/final content advances status; drafts stay in their lifecycle state.
What ships with it
12 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.
- maps/index.json 3.9 KB
- maps/links.json 682 B
- maps/manifest.json 302 B
- maps/tags.json 636 B
- README.md 1.6 KB
- references/bug-rca-report.md 5.6 KB
- references/conventions-recap.md 2.3 KB
- references/link-graph.md 2.1 KB
- references/session-reporting.md 8.1 KB
- references/status-lifecycle.md 2.7 KB
- references/test-case-template.md 1.8 KB
- references/work-item-taxonomy.md 2.9 KB
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.
- 8d ago First seen · 184 lines · 319 tokens per session scan A 4487c8c195db
docs-project-management is a skill published in the GitHub repository endorphin-ai/hasbrains-agent-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 319 tokens to every session and 3,201 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
dev-cycle
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
my-projects
Navigate your projects. Get context, paths, status. Use when needing project overview or finding specific work.
dare-refine
Analisa complexidade de uma task DARE e, quando alta, quebra em sub-tasks menores. Use após gerar o DAG (para tasks HIGH/CRITICAL), quando o dev pedir refinamento manual, ou quando o escopo mudou e uma task ficou grande. Combina heurística determinística (CLI) com decisão semântica do agente.
dare-graph
Consulta e visualiza o grafo de conhecimento do projeto (tasks, arquivos, schemas, endpoints, componentes, entidades e suas relações). Mapeia o CLI dare graph.
dare-dag
Mostra o DAG estático de tasks (DARE/dare-dag.yaml): ranks, dependências e caminho crítico. Use dare dag viz para exportar o diagrama. Mapeia o CLI dare dag.