Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/bridge-pacingWrote 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/leopu00/job-hunter-team/bridge-pacing)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/bridge-pacing"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/bridge-pacing/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/leopu00/job-hunter-team/bridge-pacing"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/bridge-pacing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 46 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Prompt Injection · line 31 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00000 | $0.01627 |
| Opus 5 | $0.00000 | $0.00813 |
| Sonnet 5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00163 |
Grade A, and why
bridge-pacing 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bridge-pacing — reading the 15-min calibration tick
The bridge runs a measurement window every 15 min (aligned to :00/:15/:30/:45 UTC). At each window-close it writes one line summarising the team's actual rate — into the Sentinella's pane, not yours (push→pull, 2026-06-25). You are deliberately not pinged every quarter of an hour: she reads the tick, and wakes you only when it is worth a turn of yours. So you use this format when she forwards you the numbers, or when you go and look at a tick on your own initiative — never as something to wait for.
Message shape
[BRIDGE PACING] HH:MM UTC window=15m (effettivi Xm) samples=N |
usage=U% reset_in=Rh reset_at=THH:MM UTC (proj=P% — INFO, secondario non-driver) |
vel_team=V%/h | vel_target=T%/h (per chiudere a TGT% al reset) [schedule+ratio phase=ON] |
ratio=K kT/% (team Σ kT / Δusage) |
agenti: name=p%/h [kT/Xm → kT/h ÷ K = p%/h, share s%, cadenza c/min (n chk in Xm)] ; ... |
VERDETTO: SFORO|MARGINE|ALLINEATO ...
TGT is the dynamic target chosen by the bridge:
- 24/7 config or no schedule →
TGT=92(band center, historical default) - work-hours config + provider with weekly cap (Codex/Claude) →
TGTis the % needed at reset so the weekly budget is distributed exactly across the user's active hours. Example: office hours 9-18 on Codex Pro →TGT≈76. - work-hours config + Kimi (no weekly cap) →
TGT=92(band center fallback).
The [schedule+ratio phase=ON] tag in parentheses is the source of the target — band_center (no work-hours), schedule+ratio (full work-hours-aware), schedule+band (work-hours + Kimi fallback). Use it to debug unexpected targets.
Fields you actually use
| Field | What it tells you |
|---|---|
vel_team |
measured team rate, in budget %-points per hour |
vel_target |
rate that would land at TGT% at reset (centre of the ±10pt band around TGT) |
share s% |
per-agent weight on the total rate (Σ shares ≈ 100%) — tells you WHO to slow down |
cadenza c/min |
per-agent jht-throttle calls per minute in the window — tells you HOW MUCH to add to the config |
VERDETTO |
actionable summary; map directly to the table below |
What ships with it
6 files 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.
- 11d ago First seen · 77 lines · 0 tokens per session scan A 331f35421235
bridge-pacing is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,627 tokens. 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 2026-08-30.
Other skills, from other repositories
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.