accountability-mirror
Skill1 starsChanged 7 months agoMITView on GitHub
Weekly hard self-check. Goggins-style accountability mirror, minus the bravado. Four questions about what you are avoiding, lying to yourself about, letting slip, and committing to fix. Use when you feel the self-story drifting.
In this repository34 other files it gives its agents.
- annual-physicalSkill
- bills-and-subsSkill
- brotherhoodSkill
- conscious-spendingSkill
- date-nightSkill
- decision-journalSkill
- discomfort-doseSkill
- emotion-coachSkill
- enough-checkSkill
- errand-batchSkill
- evening-examenSkill
- father-reviewSkill
- friend-reach-outSkill
- gratitudeSkill
- hard-conversationSkill
- home-maintenanceSkill
- kid-oneononeSkill
- love-map-refreshSkill
- mentor-touchSkill
- money-dateSkill
- morning-resetSkill
- parent-checkinSkill
- partner-checkinSkill
- partner-reviewSkill
- repairSkill
- resetSkill
- screwupSkill
- shutdown-ritualSkill
- sleep-protocolSkill
- training-planSkill
- values-checkSkill
- virtue-reviewSkill
- weekly-reviewSkill
- weekly-serviceSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Ask the user each of these out loud.
- Distinctive: line 31
No blame of others. The mirror is for you.
- Distinctive: line 32
No wallowing. This is a 10-minute tool, not a therapy session.
- Distinctive: line 51
If the user had a commitment from last week that they did not do, do NOT let it slide.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/accountability-mirror
Stand in front of a mirror if you can. Not joking. The practice loses something on a screen.
This is a short, uncomfortable, important ritual. 10 minutes.
The four questions
Ask the user each of these out loud. They answer, you capture.
- What am I avoiding?
- Name the one conversation, decision, workout, task, or fact about my life that I am actively not looking at.
- Where am I lying to myself?
- Where is the story I tell nicer than the data? "I'm getting enough sleep." "I'm present with my kids." "I'm in shape." "I still make time for friends." Where does the story not match the calendar?
- What standard am I letting slip?
- Something I used to hold myself to that I have quietly renegotiated. Health, work quality, how I speak to my partner, what time I get up. Name the drift.
- What is the one corrective action I commit to this week?
- One. Not five. Specific. Observable. Scheduled.
Constraints on the answers
- No "I should." Either "I will, by
<date>," or strike it. - No blame of others. The mirror is for you.
- No wallowing. This is a 10-minute tool, not a therapy session. If something needs more than 10 minutes, note it and consider professional support.
Output
Append to ~/adulting-data/journal/mirror-log.md:
# <date>
Avoiding: <...>
Lying to self about: <...>
Standard slipping: <...>
Corrective action this week: <...>
Due by: <specific day>
## Last week's commitment
<did I do it? Y/N. if N, why not?>If the user had a commitment from last week that they did not do, do NOT let it slide. Ask:
- Was it the wrong commitment?
- Was it the wrong size?
- Was there a real obstacle, or did you just not do it?
Then they set this week's commitment with eyes open.
End with one line: "Put the action on the calendar before you close this."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

