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 msinclair25/mdevolved --skill owd-albatrossgit clone --depth 1 https://github.com/msinclair25/mdevolvedWrote 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/msinclair25/mdevolved/owd-albatross)<a href="https://agentmods.dev/skills/msinclair25/mdevolved/owd-albatross"><img src="https://agentmods.dev/badge/skills/msinclair25/mdevolved/owd-albatross/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/msinclair25/mdevolved/owd-albatross"><img src="https://agentmods.dev/badge/skills/msinclair25/mdevolved/owd-albatross.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 | $0.00093 | $0.01628 |
| Opus 5.5 | $0.00037 | $0.00651 |
| Sonnet 5.5 | $0.00019 | $0.00326 |
| Haiku 4.5 | $0.00009 | $0.00163 |
Grade A, and why
owd-albatross 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 26d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDevolved + Albatross
Legacy compatibility path. New setups should use
mdevolved-albatross; keep this pack for existingowdconfigurations and receipts.
Keep one universal MDevolved server. Apply this profile only as Albatross-side configuration and instructions; never change MDevolved framing, OAuth, tool schemas, Project lifecycle, or server-side authority.
Confirm the runtime
- Confirm the repository uses Albatross and inspect
agent.config.json,.albatross/prompt.md,.owdignore, andAGENTS.mdwhen present. - Preserve every existing Albatross option and MCP server.
- Use the deployment's exact HTTPS
/mcpURL. Plain HTTP is allowed only for localhost development. - Use MCP server name
owd; Albatross exposes its tools asmcp__owd__<tool>.
Albatross 2.5.0 supports child-process stdio MCP only. Use the profile's
pinned [email protected] bridge with --transport http-only. This is a
temporary client adapter, not an MDevolved proxy or protocol fork. Remove it when
Albatross supports authenticated remote Streamable HTTP natively.
Do not add a static bearer token, custom Project call, translated tool schema, client-side authorization rule, or a second MDevolved endpoint.
Preserve participant identity
The bridge configuration includes a non-secret
X-OWD-Albatross-Participant header. The pinned bridge includes custom headers
in its OAuth cache key:
- Reusing
primarymeans the Albatross sessions are one MDevolved OAuth participant. - A genuinely independent writer or reviewer uses another safe ID such as
reviewerand completes a separate authorization. - A new session,
/reset, path fork, model, or display name using the same ID is still the same MDevolved participant.
The header partitions local credential storage; it is not a credential and grants no access. MDevolved OAuth identity and live server-side grants remain authoritative.
Install without overwriting
Prefer the authenticated MDevolved dashboard's Copy Albatross setup kit action. It generates one fresh, internally consistent participant ID across these steps. Choose New participant ID before copying a kit for another workspace or independently attributable reviewer.
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.
- 26d ago Changed a919220d8d89
- 1mo ago Changed e6d3b2152e17
- 1mo ago First seen · 144 lines · 93 tokens per session scan A 7bfe57292e0d
owd-albatross is a skill published in the GitHub repository msinclair25/mdevolved (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,628 once invoked, about $0.0004 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 2026-09-01.
Other skills, from other repositories
triage-tasks
Use when you want to review and batch-update open vault task statuses for the current project or across all projects.
tackle-task
Use when starting work on a specific vault task, when a task title or path is mentioned, or when coming from triage output.
add-task
Use when you want to quickly capture a new task in the vault from a title, with optional priority and due date.
ariadne:workstream-tracking
Create, audit, or improve Obsidian Kanban work boards and Dataview dashboards for durable project, roadmap, evaluation, implementation, QA, or recurring workstream tracking inside an agent-maintained vault.
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
pkm-session-end
Use when wrapping up a work session — creates devlog entry, captures undocumented decisions/research/debugging, audits link health of session work, and updates project index. Primarily used via the pkm-capture agent.