Agent skill

Price Alert

by aeonfun in aeonfun/aeon

Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed.

MITAuto-check passed

Install Price Alert

skills CLI
$ npx skills add aeonfun/aeon --skill price-alert -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aeonfun/aeon price-alert --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aeonfun/aeon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/price-alert .claude/skills/price-alert && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
price-alert
GitHub stars
767
Token cost
~4k tokens
SKILL.md length
1,804 words
Files
1
Skills in repo
82
Repo updated
First seen
Licence
MIT

At a glance

Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed.

  • Works in 9 steps: Parse var → Resolve tracked token → Fetch current price (DexScreener primary) → …
  • SKILL.md covers Why this exists, Config, State schema and Steps, plus 3 more sections
  • Calls jq and curl; reaches api.dexscreener.com; needs PRICE_ALERT_NO_TOKEN

What it does

Price Alert is an agent skill from aeonfun/aeon. Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed. Silent on normal days.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget… The licence is MIT.

Example prompts

  • “/price-alert”

Requirements

  • A credential in PRICE_ALERT_NO_TOKEN

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Parse var
  2. Resolve tracked token
  3. Fetch current price (DexScreener primary)
  4. Evaluate ATH gate
  5. Evaluate sharp-move gate
  6. Evaluate target-crossing gate
  7. Combine verdicts and notify
  8. Persist state
  9. Log

What it can do on your machine

Read from SKILL.md and the folder at commit c0cb7c4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.dexscreener.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PRICE_ALERT_NO_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Price Alert loads about 4k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 1,804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aeonfun/aeon at commit c0cb7c4, republished under its MIT licence (© aeonfun). 1,804 words, ~4,024 tokens.

Download SKILL.mdSave it as .claude/skills/price-alert/SKILL.md (or your agent's skills folder).
name
price-alert
description
Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed. Silent on normal days.
metadata.title
Price Alert
metadata.category
basics
metadata.tags
crypto

${var} — Optional. Pass one or more target_price levels (comma-separated USD numbers, scientific notation allowed) to fire a one-time alert when the price crosses any of them. Empty = only ATH and sharp-move gates run. Pass dry-run to skip notify (state still updates). Pass set-target:<price> — the shape the Telegram force-reply sends (step 7) — to register a target and get a one-line confirmation.

Today is ${today}. The scheduled digests (digest, token-movers, ...) run at fixed hours. None of them tell the operator "the price just hit a new high" or "the token moved 28% in the last hour" — both are events that warrant attention the moment they happen, not 14 hours later in a daily digest. This skill closes that window.

Why this exists

Scheduled daily digests are calm summaries. Real moves need real-time signal. Three classes of move are worth a same-day ping:

  • New all-time high. The single most narrative-shaping price event a token can have. Worth marking on the timeline regardless of size.
  • Sharp 1h moves (±20%). Either a buyer wave or a liquidation cascade — both change what the operator does next (post about it, watch for follow-through, check the chart).
  • Operator-set target crossings. The operator may want to know when price clears $X (often a personal stretch goal or a level tied to a tweet/launch). One alert per target per direction.

Everything else is noise not worth a same-day ping.

Config

Reads:

  • memory/MEMORY.md "Tracked Token" section — the tracked token's contract/chain. If absent, exit silently.
  • memory/topics/price-alert-state.json — last-known ATH, last-alert timestamps per event type, target-crossing history. Created with defaults on first run.

Writes:

  • memory/topics/price-alert-state.json — updated state every run.
  • memory/logs/${today}.md — one log block per run, even on OK.
  • Notification via ./notify — only when a gate fires.

No new secrets. Uses keyless DexScreener; falls back to WebFetch when a public curl GET is flaky (there is no network sandbox).

State schema

json
{
  "contract": "0xbf8e8f0e8866a7052f948c16508644347c57aba3",
  "chain": "base",
  "ath": {
    "price_usd": 0.000003757,
    "observed_at": "2026-05-10T19:00:00Z",
    "announced_at": "2026-05-10T19:30:00Z"
  },
  "last_alerts": {
    "ath": "2026-05-10T19:30:00Z",
    "sharp_move": null,
    "target_hit": null
  },
  "targets": {
    "0.000005": {
      "side": "above",
      "first_seen_below_at": "2026-05-11T08:00:00Z",
      "hit_at": null,
      "announced_at": null
    }
  }
}

Key invariants:

  • ath.price_usd only ever monotonically increases. If a run sees a lower price than the stored ATH, leave the ATH alone.
  • last_alerts.* powers the 4h dedup window. Each gate has its own clock.
  • targets.${price}.side is above if current_price < target when the target was first observed (operator is waiting for the price to climb to it), and below otherwise. Set once, never flipped.
  • targets.${price}.hit_at is set the run the cross happens. announced_at is set the run the notification fires. They differ only if the run lands inside a dedup window — but target alerts never re-fire, so hit_at == announced_at in practice.

Steps

1. Parse var
  • If ${var} starts with set-target: → set FROM_REPLY=1, MODE=execute. Strip the set-target: prefix (${var#set-target:}); the remainder is the target(s) list, parsed exactly like the comma-split below. This is the shape scripts/telegram-route.sh sends when the operator replies to the step-7 force-reply prompt. The run proceeds normally (register the target, don't fire on first observation) and closes the loop with a confirmation in step 7.
  • Else if ${var} matches ^dry-run → MODE=dry-run. Strip the prefix; remainder (if any) is treated as targets.
  • Otherwise MODE=execute.
  • Split the remainder on , (commas) and strip whitespace.
  • For each token: if it parses as a positive float (scientific notation OK, e.g. 5e-6), include it. Reject zero / negative / non-numeric tokens and log PRICE_ALERT_BAD_TARGET: ${token} — continue with the surviving targets.
  • If after filtering the remainder was non-empty but yielded zero valid targets → log PRICE_ALERT_BAD_VAR: ${var} and exit. Normally no notify — but if FROM_REPLY=1, first close the loop with ./notify "Couldn't read \"${var#set-target:}\" as a price. Reply with a number like 0.000005." (a force-reply always deserves an acknowledgement).
  • If the remainder was empty, TARGETS=() is fine — ATH and sharp-move gates still run.
2. Resolve tracked token
bash
mkdir -p memory/topics
[ -f memory/topics/price-alert-state.json ] || cat > memory/topics/price-alert-state.json <<'EOF'
{"contract":null,"chain":null,"ath":null,"last_alerts":{"ath":null,"sharp_move":null,"target_hit":null},"targets":{}}
EOF

Parse the "Tracked Token" table in memory/MEMORY.md. Pull CONTRACT (column 2 of the first data row) and CHAIN (column 3, lowercased). If the section is missing, the table is empty, or the contract field doesn't match ^0x[0-9a-fA-F]{40}$ → log PRICE_ALERT_NO_TOKEN and exit (no notify, no state write).

If the state file's contract is set and differs from the resolved contract → log PRICE_ALERT_TOKEN_CHANGED and reset the state file to defaults with the new contract/chain. ATH starts over with the new token.

3. Fetch current price (DexScreener primary)
bash
RESP=$(curl -fsS "https://api.dexscreener.com/latest/dex/tokens/${CONTRACT}" 2>/dev/null || echo "")

If the response is empty, falsy, or jq can't parse it → fall back to WebFetch on the same URL with prompt "Return the raw JSON body verbatim." and try again. If both paths fail → log PRICE_ALERT_FETCH_FAIL and exit with status ERROR (no notify, no state mutation beyond touching last_run_at).

From the parsed JSON:

  • Filter .pairs[] to entries where .chainId == "${CHAIN}".
  • Of those, pick the entry with the highest .liquidity.usd — call this the deepest pool. If no pair matches the chain, fall back to the highest-liquidity pair across all chains and mark chain=fallback in the log.
  • Extract: CURRENT_PRICE=.priceUsd (float), H1_CHANGE_PCT=.priceChange.h1 (float, may be missing → treat as 0), H24_CHANGE_PCT=.priceChange.h24 (float, may be missing → treat as 0), POOL_URL=.url.

If CURRENT_PRICE is missing, zero, or non-numeric → log PRICE_ALERT_BAD_PRICE and exit ERROR.

4. Evaluate ATH gate
prior_ath = state.ath.price_usd  (null on first run)
new_ath   = (prior_ath is null) OR (CURRENT_PRICE > prior_ath)

If new_ath:

  • Always update state.ath.price_usd = CURRENT_PRICE, state.ath.observed_at = NOW.
  • Notify only if the last ath alert was >4h ago (or never). On the first run after token initialisation, suppress the notification (we don't know if this is genuinely an ATH or just the starting baseline) — set state.ath.announced_at = NOW so subsequent strict-higher prices alert correctly.
  • If suppressed because prior_ath is null (first run), record verdict ATH_BASELINE for the log; no notify.
  • Otherwise verdict for this gate is ATH.
5. Evaluate sharp-move gate
sharp = abs(H1_CHANGE_PCT) >= 20.0

If sharp:

  • If state.last_alerts.sharp_move is within the last 4h → verdict SHARP_MOVE_DEDUPED, no notify.
  • Otherwise verdict SHARP_MOVE, notify, set state.last_alerts.sharp_move = NOW.

Sign of H1_CHANGE_PCT decides the direction word in the message (up for ≥0, down for <0).

6. Evaluate target-crossing gate

For each target in TARGETS:

  • If the target isn't yet in state.targets: this is the first time the operator has set it. Record side (above if CURRENT_PRICE < target, else below), first_seen_below_at=NOW, hit_at=null, announced_at=null. Do not notify on first observation. This avoids "the price was already there when you set the target" noise.
  • If the target is in state.targets and hit_at is already set → skip; target-hit alerts are one-shot per side.
  • Otherwise check the cross:
    • side=above & CURRENT_PRICE >= target → crossed.
    • side=below & CURRENT_PRICE <= target → crossed.
  • On cross: set hit_at=NOW, announced_at=NOW, verdict TARGET_HIT for this target, notify (subject to 4h dedup on last_alerts.target_hit).

Targets that crossed in prior runs stay in the state file with hit_at set so they don't refire if the price wobbles back.

Show full SKILL.md (752 more words)Show less
7. Combine verdicts and notify

Run-level verdict precedence (used for the log status line and the notification ordering):

  1. ATH — strict new high after baseline.
  2. TARGET_HIT — operator-set level crossed.
  3. SHARP_MOVE — ±20% in 1h.
  4. OK — no gate fired.

If multiple gates fired in the same run, send one notification per gate. Each gate independently respects its own dedup clock — an ATH and a TARGET_HIT in the same run produce two messages; an ATH and a SHARP_MOVE_DEDUPED produce one.

Notification templates

ATH:

*$TOKEN — New ATH — ${today}*

$TOKEN just printed a new all-time high at $X.XXXXe-N.
Previous ATH: $Y.YYYYe-N (set ${prior_ath_age} ago).
24h move: ±Z.Z% · 1h move: ±W.W%

Chart: ${POOL_URL}

SHARP_MOVE:

*$TOKEN — Sharp 1h Move — ${today}*

$TOKEN ${up|down} ${abs(h1):.1f}% in the last hour — now $X.XXXXe-N.
24h: ±Z.Z%
${one of: "Buyer wave — watch for follow-through." | "Selling pressure — watch the next hour for stabilisation." }

Chart: ${POOL_URL}

(Direction phrase is hard-coded by sign: positive = buyer wave; negative = selling pressure. No freelance commentary.)

TARGET_HIT:

*$TOKEN — Target Hit — ${today}*

$TOKEN just crossed $${target} (now $X.XXXXe-N).
Direction: ${above|below}
24h: ±Z.Z% · 1h: ±W.W%

Chart: ${POOL_URL}

If MODE == dry-run: build the messages, log the planned notifications, but skip ./notify. State still updates so dedup clocks advance correctly.

Cap each message at ~2500 chars; price-alert messages are short by nature and shouldn't approach this.

Send the alert

Build each firing gate's message to a file and send it with ./notify -f alert.md (one send per gate). State still advances even on a deduped run, so the dedup clocks stay correct.

Set-a-target follow-up (force-reply)

Buttons and force_reply can't share one message, so this is a separate send. After a genuine ATH alert (post-baseline, not a deduped repeat), and only when no un-hit operator target currently sits above CURRENT_PRICE (don't nag operators who already queued one), offer to capture the next level:

bash
./notify "New high — want an alert when $SYMBOL clears a level above this? Reply with a price." \
  --force-reply --placeholder "e.g. 0.000005" \
  --context "price-alert::set-target"

The reply routes back as var=set-target:<price> (handled in step 1). On that run, once the target is registered (step 6, first-observation — no cross alert), close the loop with a one-line confirmation: ./notify "Target set: \$<price> for $SYMBOL — I'll alert you when it crosses." (Send it only when a new target was actually registered this run.)

8. Persist state

Rewrite memory/topics/price-alert-state.json atomically:

bash
TMP=$(mktemp)
jq --arg ts "$(date -u +%FT%TZ)" '
  .last_run_at = $ts |
  .contract = $contract |
  .chain = $chain |
  .ath = $ath_obj |
  .last_alerts = $last_alerts_obj |
  .targets = $targets_obj
' memory/topics/price-alert-state.json > "$TMP"
mv "$TMP" memory/topics/price-alert-state.json

Validate with jq empty memory/topics/price-alert-state.json after writing; if it fails, restore from a .bak copy and log PRICE_ALERT_STATE_CORRUPT. Keep one .bak rolling.

Cap state.targets to 20 most-recent entries (LRU by first_seen_below_at) so a long-running fork doesn't accumulate stale operator targets.

9. Log

Append to memory/logs/${today}.md under a ### price-alert heading:

### price-alert
- **Skill**: price-alert
- **Token**: ${SYMBOL} (${CONTRACT})
- **Current**: $X.XXXXe-N | 1h: ±W.W% | 24h: ±Z.Z%
- **ATH**: $Y.YYYYe-N (set ${YYYY-MM-DD HH:MM} UTC) [${UNCHANGED|NEW}]
- **Sharp-move gate**: ${FIRED|QUIET|DEDUPED}
- **Targets evaluated**: ${comma-list of target prices} → ${comma-list of per-target verdicts}
- **Verdicts fired**: ${comma-list, or NONE}
- **Notifications sent**: ${N}
- **Status**: ${PRICE_ALERT_OK | PRICE_ALERT_ATH | PRICE_ALERT_SHARP_MOVE | PRICE_ALERT_TARGET_HIT | PRICE_ALERT_DRY_RUN | PRICE_ALERT_NO_TOKEN | PRICE_ALERT_TOKEN_CHANGED | PRICE_ALERT_FETCH_FAIL | PRICE_ALERT_BAD_PRICE | PRICE_ALERT_BAD_VAR | PRICE_ALERT_STATE_CORRUPT}

The status field carries the highest-priority gate fired this run, or the most relevant error. OK means the run completed cleanly and no gate fired.

Exit taxonomy

StatusMeaningNotify?
PRICE_ALERT_OKRun completed, no gate firedNo
PRICE_ALERT_ATHNew strict all-time high (post-baseline)Yes
PRICE_ALERT_SHARP_MOVE±20% in 1h, outside dedup windowYes
PRICE_ALERT_TARGET_HITOperator target crossed for the first timeYes
PRICE_ALERT_DRY_RUNvar=dry-run modeNo (state still updates)
PRICE_ALERT_NO_TOKENNo tracked token configured in MEMORY.mdNo
PRICE_ALERT_TOKEN_CHANGEDTracked contract changed since last run; state resetNo
PRICE_ALERT_FETCH_FAILBoth curl and WebFetch failedNo
PRICE_ALERT_BAD_PRICEAPI returned malformed/zero priceNo
PRICE_ALERT_BAD_VAR${var} had non-empty, non-dry-run text but yielded zero valid targetsNo
PRICE_ALERT_STATE_CORRUPTjq validation failed after write; restored from .bakNo

Network note

DexScreener is keyless and public — curl works; there is no network sandbox. If a public curl GET is flaky, the WebFetch fallback kicks in (built-in Claude tool, prompt: "Return the raw JSON body verbatim."). There's no auth header, and the URL doesn't change between runs. Notify goes through ./notify, which stages to .pending-notify/; the workflow re-delivers any messages that failed to send after the run — no extra script needed.

Constraints

  • One alert per event per 4h window. The state file's last_alerts.* map is the only authority on whether to suppress.
  • Target alerts are one-shot per side. Once hit_at is set, the target never re-fires — even if the price wobbles back through the level. Operators add new targets if they want continued signal.
  • No baseline alert. The first run after a fresh state file or token change must NOT send an ATH notification — the stored price is the baseline, not a "new high." Subsequent strict-higher prices alert.
  • No freelance interpretation. The sharp-move direction phrase is hard-coded by sign. Do not embellish with TA opinions ("looks like distribution", "could test support"). The verdict tells the operator what happened; the operator decides what it means.
  • Liquid-pool selection only. The deepest-liquidity pair on the configured chain wins. Don't compute prices from blended pool averages — the deepest pool's priceUsd is the canonical mark.
  • State writes are atomic + validated. Every state write goes through a tmpfile + jq empty validation step. Corrupt writes restore from .bak.
  • Read-only across memory/logs/. This skill never modifies past log files. It only appends to today's.
  • Targets are absolute USD, not percentages. This avoids ambiguity ("20% from where?"). If operators want move-from-now alerts they have the sharp-move gate.
  • Idempotent under same-minute reruns. Same-minute reruns with identical price input produce identical state and zero new notifications (every gate dedup-suppressed).

© aeonfun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/price-alert of aeonfun/aeon.

Open the folder on GitHubat commit c0cb7c4

Compare with similar skills

Price Alert next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Price Alert compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Price Alert this skillaeonfun/aeon767—~4kAutomated safety check: PassMIT
Authoring Error Tracking AlertsPostHog/posthog40k—~2.8kAutomated safety check: PassCustom licence
Pricingsickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassMIT
Tracking Crypto Pricesjeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: PassMIT
Pricing Strategyphuryn/pm-skills27k—~913Automated safety check: PassMIT
Pricing Strategyalirezarezvani/claude-skills28k1 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Official

    Author error tracking alerts that fire when an issue is created, reopened, or starts spiking.

    40k GitHub stars~2.8k tokensUpdated today
    Backend & APIsAuto-check passed
  • Pricing

    sickn33/agentic-awesome-skills

    When the user wants help with pricing decisions, packaging, or monetization strategy.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    Sales & SupportAuto-check passed
  • Tracking Crypto Prices

    jeremylongshore/tons-of-skills-marketplace

    Track real-time cryptocurrency prices across exchanges with historical data and alerts.

    2.8k GitHub stars~1.1k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Pricing Strategy

    phuryn/pm-skills

    Analyze and design pricing strategies including pricing models, competitive pricing analysis, willingness-to-pay estimation, and price elasticity.

    27k GitHub stars~913 tokensUpdated 25 days ago
    Sales & SupportAuto-check passed
  • Pricing Strategy

    alirezarezvani/claude-skills

    Design, optimize, and communicate SaaS pricing — tier structure, value metrics, pricing pages, and price increase strategy.

    28k GitHub starsUsed in 1 repo~3.5k tokens
    Sales & SupportAuto-check passed
  • Pricing Strategist

    alirezarezvani/claude-skills

    A skill your agent uses when designing or revisiting product pricing — selecting a pricing model (subscription seat-based, usage-based, value-based, freemium, or hybrid), running Van Westendorp…

    28k GitHub stars~2.3k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

More from aeonfun/aeon

All 82 skills in this repo
  • Browses open tasks on the TaskMarket agent-worker market and, with explicit operator approval, creates tasks, tracks submissions and submits finished work.

    767 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Sets up and manages an Aeon agent instance that runs skills on a schedule through GitHub Actions: starting, rescheduling, debugging, editing skills and mining chat history.

    767 GitHub stars~9k tokensUpdated yesterday
    Auto-check: warnings
  • Reads a Base Account's address, portfolio and transaction history through the Base MCP server, and stays strictly read-only in unattended Aeon runs, reporting only changes.

    767 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Audits every page of a site each day from its sitemap, scores on-page and technical SEO, checks duplicates across pages and reports what changed since the last run.

    767 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed
  • Action Converter

    aeonfun/aeon

    5 concrete real-life actions, leverage-scored against open loops with specificity and anti-fluff gates

    767 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Aeon Config Doctor

    aeonfun/aeon

    Static linter for an Aeon instance's configuration that catches silent failures such as unquoted schedules, duplicate keys, unconfigured skills and broken MCP references.

    767 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed

Questions about Price Alert

What does Price Alert do?

Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed. Price Alert is an agent skill from aeonfun/aeon. Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed.

How do I install Price Alert in Claude Code?

Run `npx skills add aeonfun/aeon --skill price-alert -a claude-code`. Or copy the skill folder (skills/price-alert in aeonfun/aeon) into .claude/skills/price-alert in your project. Claude Code loads it when a task matches its description.

How do I install Price Alert in Codex?

Run `npx skills add aeonfun/aeon --skill price-alert -a codex`. Or copy the skill folder (skills/price-alert in aeonfun/aeon) into .agents/skills/price-alert in your project. Codex loads it when a task matches its description.

Can I use Price Alert in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aeonfun/aeon --skill price-alert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/price-alert, .gemini/skills/price-alert, .github/skills/price-alert and .opencode/skills/price-alert in your project.

What does Price Alert need to run?

Going by SKILL.md and its folder, Price Alert needs the command-line tools its instructions call (jq and curl) and credentials named PRICE_ALERT_NO_TOKEN. Our summary lists: A credential in PRICE_ALERT_NO_TOKEN.

Does Price Alert access the network?

SKILL.md names 1 domain. In commands or code: api.dexscreener.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Price Alert safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Price Alert use?

Price Alert is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Price Alert use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Price Alert?

Skills that share tags, products or a category with Price Alert: Authoring Error Tracking Alerts (PostHog/posthog, 40k stars), Pricing (sickn33/agentic-awesome-skills, 47k stars), Tracking Crypto Prices (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Pricing Strategy (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Price Alert?

aeonfun (a GitHub organization) maintains it in aeonfun/aeon, which has 767 GitHub stars. The repository holds 82 skills in this directory. The repository was last updated on October 8, 2026.

Source: aeonfun/aeon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.