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 wrg32786/aigent-os --skill timeline-calibrationgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/timeline-calibration)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/timeline-calibration"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/timeline-calibration/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/wrg32786/aigent-os/timeline-calibration"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/timeline-calibration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00919 |
| Opus 5 | $0.00028 | $0.00460 |
| Sonnet 5 | $0.00011 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
Timeline Calibration 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Timeline Calibration
[!danger] HARD RULE — fires whenever you're about to quote a timeline If the Caddy hint for this skill surfaces, you are about to quote a timeline using human-developer anchors. STOP. Recalibrate.
The recalibration table
| You're about to say | Reality | Self-correct to |
|---|---|---|
| "hours" of work | a few minutes | minutes, often <5 |
| "a couple hours" | ~2-5 min | "a few minutes" |
| "half a day" | ~5-10 min | "5-10 minutes" |
| "a day" | ~10-15 min | "~10 minutes this session" |
| "a few days" | ~15-30 min | "~20-30 minutes focused work" |
| "a week" | ~30-60 min | "30-60 minutes focused" |
| "a few weeks" | ~1-2 hours | "~an hour or two" |
Why
- An AI's execution speed is not what its training data anchors expected. Training data was calibrated on human-developer pair-programming or solo-dev cycles.
- The bottleneck is NOT writing speed. It's: context-load (reading files), decision rounds with the principal, and ambiguity resolution.
- The principal calibrates their attention around your estimates. Quoting "12 hours" for what takes 10 minutes wastes their planning capacity AND makes the agent look slow.
Calibration anchors
- 1 file write with material in context = ~5 seconds
- 1 file edit = ~3 seconds
- 1 small SKILL.md = ~15 seconds
- 1 medium concept note with cross-refs = ~20 seconds
- 5-10 file build in parallel writes = 1-2 minutes
- "Track of work" with 5-15 files = 2-5 minutes
- Whole "v0.2"-class release with 30+ artifacts = 5-15 minutes
- Multi-track release stacking (25+ files across 2 commits) = under 10 minutes wall-clock
Decision rule when about to quote a timeline
Ask: is the bottleneck me or external?
- Me (writing files, code, notes) → divide human-dev estimate by 30-60x
- External (waiting for principal approval, web fetches, running pipelines) → count the external clock honestly
- Mixed → split the estimate: "5 min focused work + 10 min waiting on review"
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.
- 9d ago First seen · 73 lines · 56 tokens per session scan A 70fb76f0aea9
Timeline Calibration is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 919 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
send-email
Compose and send a one-off email to a named recipient via Resend - written in the operator's voice, then sent in-run through the shared send caps with an operator audit copy.
chief-of-staff
Act as the user's chief of staff, not a task-taker. Use for planning a day or week, triaging priorities, prepping for meetings or calls, drafting messages on the user's behalf, tracking commitments and follow-ups, reviewing what's in-flight, or any moment the user wants a trusted operator who knows their context.…
RemoteTeamCommander
Complete operating system for remote and distributed teams — async communication, time zone equity, virtual culture, performance management at a distance, and preventing remote-class citizens.
meeting-analyzer
Activates MeetingAnalyzer for extracting intelligence from meeting transcripts, notes, and recordings. Use when you need to extract action items with owners and due dates, identify decisions made, summarize key discussion points, detect unresolved conflicts or blockers, or generate a structured meeting follow-up email.
Loop
Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "/15 "), records the schedule, and acknowledges back to the user.
Batch Run
Apply the same prompt or operation to a list of items in turn, collecting results. Useful for "do X to each of these files / PRs / records" tasks.