Borrowing it
Nothing to install: this file belongs to AlexanderMattTurner/agent-glovebox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlexanderMattTurner/agent-glovebox/main/.claude/skills/doctrine-capture/SKILL.mdgit clone --depth 1 https://github.com/AlexanderMattTurner/agent-gloveboxWrote 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/alexandermattturner/agent-glovebox/doctrine-capture)<a href="https://agentmods.dev/skills/alexandermattturner/agent-glovebox/doctrine-capture"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/doctrine-capture/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/alexandermattturner/agent-glovebox/doctrine-capture"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/doctrine-capture.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 | $0.00211 | $0.01538 |
| Opus 5.5 | $0.00084 | $0.00615 |
| Sonnet 5.5 | $0.00042 | $0.00308 |
| Haiku 4.5 | $0.00021 | $0.00154 |
Grade C, and why
doctrine-capture scanned grade C with 1 finding 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 3d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
3. **Root `CLAUDE.md`** takes it only when it must fire BEFORE any file is opened, or must override the system prompt. That is a small set, and everything else that lands there taxes every unrelated session. How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing a NEVER or an ALWAYS
The doctrine
A capitalised NEVER or ALWAYS from the user is a standing rule, and you are the only one who will ever hear it. The conversation ends and the next session starts from the committed tree, so a rule you merely obey this turn is a rule you deleted. Obey it now AND write it down, in the same turn.
A doctrine change needs no approval. Root CLAUDE.md § Guard budget asks only that it be LOUDLY ANNOUNCED in the PR description. Write a standing rule the user just stated without asking, and quote their sentence in the PR body. Apply the § What is NOT doctrine test below first, and write nothing when the test does not pass.
Fix the instance first, then the rule.
A complaint about the session's process is a capture too
When the user faults how this session ran, or calls a fix a patch, fix the instance at its cause, then capture the rule in the same turn without waiting to be asked. Find the doctrine sentence or tool that let it happen and REWRITE it. The doctrine files net zero lines or fewer: pay each clause you add by cutting an argument, an anecdote or a restatement, in that file first. Read git diff --numstat on the capture commit before you push it. Prefer the tool: a rule the session must obey under momentum belongs on the tool-use loop (prompt-authoring.md). Worked case: a session babysitting "even PRs" saved its set --bounded, so it sat with zero agents while seven even PRs went unwatched. The capture gave babysit-next.py a --parity rule that refills at every run.
A defect class you notice is a capture too
Do not wait for the user to complain. When you notice a defect CLASS — a third copy of a helper, a rule a sub-agent broke, a finding you are about to write under ## Also noticed — fix the instance, then find the rule that should have stopped it. No rule: write one. A rule that exists but did not fire: move it to where it fires — the sub-agent brief, the skill the activity loads, a hook. Worked case: an open PR added a third "is the process gone" helper, and the session only recorded it. The capture widened code-style.md's one-reader rule from grammars to every job, and made every implementation brief report the definitions it added.
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.
- 3d ago Changed · +6 tokens per session 49814b9821d1
- 15d ago Changed · +4 lines · +33 tokens per session 0b0352e7cddb
- 16d ago Changed · +29 tokens per session cf857286fbdd
- 24d ago Changed · +4 lines · +47 tokens per session 02a53bc92600
- 1mo ago Changed · +9 lines scan D → C e190659189d8
- 1mo ago Changed scan C → D 944586afd901
- 1mo ago Changed cff274df7041
- 1mo ago First seen · 45 lines · 96 tokens per session scan C ce91fe8cc42e
doctrine-capture is a skill published in the GitHub repository AlexanderMattTurner/agent-glovebox (68 stars, last pushed today), licensed Apache-2.0. It adds 211 tokens to every session and 1,538 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.