Execute research tasks — checklist soft gate, phase dispatch with explicit thesis_dir, budget enforcement (halt + approval card on overrun), skill_pin recording (version_hash content-hashed per skill directory), [x] written on completion.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# agentii.implement
## Before dispatch
1. **Checklist soft gate (Q29)**: scan `checklists/*.md`; on unchecked items, stop
and ask — the human may proceed (it is a soft gate, not a hard block).
2. **Budget check (Q58)**: `budget{max_tasks, max_retries_per_task}` — exceeding
halts with a Q39 approval card; never a silent overrun. The dispatcher checks
budget first, `max_in_flight` second (Q82).
3. **Resume matrix (Q56)**: absent → run; valid FR-090 → skip; corrupted →
`--resume`; `stale` → leave for converge. The filesystem IS the checkpoint.
4. **`thesis_dir` passed explicitly** (Q37) — no singleton pointer; cwd fallback is
human-only and journaled.
## During dispatch
- Cross-vertical handoff passes artifact **paths, never content** (Q13 rule 3).
- `skill_pin: {skill_name: version_hash}` recorded before the first task
(`version_hash` = content hash of SKILL.md + `references/`); a version change
mid-thesis uses the new version and **appends** the new hash (Q57).
- `[x]` written on completion — display-only; converge never reads it.
## Invocation
```bash
# Resolve the kit root first — contracts/kit-root.md. The kit's scripts do NOT ship
…
The line at the top of this page pins the label git:20260919.eaccfbe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_qha53xcn7y5z3aif
GET https://markdownregistry.com/api/v1/resolve?ref=agentii-ai/agentii-investment-intelligence/implement
GET https://markdownregistry.com/api/v1/blob/27b951d74f5ee87b23b2dc26e10aab3b0e603d4da29ee85f4624fd5136df2da9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
agentii-ai/agentii-investment-intelligence · SKILL.md · Institutional-grade equity research skills for AI agents. 80 Claude-type skills across 14 verticals…
agentii-ai/agentii-investment-intelligence · marketplace-beachhead/plugins/bio-pharm/skills/agentii/fda-catalyst-vaccines/SKILL.md · Vaccine catalyst analysis across the two-gate path: CBER BLA review and the ACIP recommendation gate that turns FDA…
agentii-ai/agentii-investment-intelligence · marketplace-beachhead/plugins/bio-pharm/skills/agentii/med-event-takeaways/SKILL.md · Post-event analyst note (conferences, KOL events, site visits) with the professional note anatomy — headline verdict…
agentii-ai/agentii-investment-intelligence · marketplace-beachhead/plugins/bio-pharm/skills/agentii/peer-bench-med/SKILL.md · Med peer benchmarking: select actual biotech/pharma peers via the med universe (drug/indication overlap where possible)…
rsmdt/the-startup · plugins/start/skills/implement/SKILL.md · Implementation entry point. Use to execute a completed specification. Reads the spec's slice and scenario tasks from…
posit-dev/skills · posit-dev/implement/SKILL.md · Orchestrates implementation of a plan file by delegating work to subagents in parallel. Verifies git branch state…
ericrisco/rsc-harness · skills/implement/SKILL.md · Use when an approved plan and task list exist and it is time to turn them into working, reviewed code — ASDD stage 4…
boshu2/agentops · packs/agentops-executor/agents/implementer/skills/implement/SKILL.md · Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check…
boshu2/agentops · plugin/skills/implement/SKILL.md · Make the code change a ticket or bug report asks for, then prove it with the repo''s own checks. Use when: told to fix…
boshu2/agentops · packs/agentops-executor/agents/implementer-claude/skills/implement/SKILL.md · Execute one bounded RED to GREEN experiment from bead or caller intent; return derived subject identity and check…
boshu2/agentops · skills/implement/SKILL.md · Make the code change a ticket or bug report asks for, then prove it with the repo''s own checks. Use when: told to fix…
